If you want to learn:

- What is ElevenLabs and how does it compare to other AI voice platforms?

- How do you get started with ElevenLabs voice agents in minutes?

- What's the difference between the Creative Platform and Agents Platform in ElevenLabs?

- How much does ElevenLabs cost and is there a free tier available?

- Why is ElevenLabs considered the industry leader for human-like voice AI?

- How do you create your first conversational AI agent using the ElevenLabs platform?

Then this lecture is for you!

This lecture introduces you to the ElevenLabs voice AI platform, focusing on building conversational AI agents with human-like voice quality. You'll discover why ElevenLabs is considered the leading enterprise-grade solution for AI voice agents, exploring both the Creative Platform for voice synthesis and text-to-speech, and the Agents Platform for deploying conversational agents across voice and chat.

You'll learn about ElevenLabs pricing options, including the free tier that lets you get started with AI agents without cost, and understand the platform's low latency, expressive voice capabilities that feel natural in customer conversations. The lecture walks you through the ElevenLabs interface, demonstrating the agent platform's workflow builder where you'll configure, monitor, and deploy AI voice agents.

By the end of this session, you'll understand how ElevenLabs offers advanced AI voice technology with impressive voice quality, supports integration with automation tools, and provides the foundation for building powerful conversational AI voice agents. You'll complete your account setup, navigate the platform's key features including the Configure, Monitor, and Deploy sections, and prepare to create your first voice agent from scratch using this cutting-edge voice AI solution.

If you want to learn:

How to build your first conversational AI voice agent from scratch as a complete beginner?

What are the step-by-step instructions to create a real-time voice agent using ElevenLabs and Gemini?

How can you add conversational AI capabilities to automate customer support and enhance user interactions?

What's the easiest way to integrate knowledge bases and customize AI voice agents for specific use cases?

How do ElevenLabs agents deliver low-latency, human-like conversations with natural-sounding voices?

Then this lecture is for you!

In this hands-on tutorial, you'll build your first AI voice agent using the ElevenLabs conversational AI platform and Gemini 2.5 Flash. You'll start by creating a blank agent, configuring the system prompt, and selecting a voice to establish your assistant's personality. Through step-by-step demonstrations, you'll test real-time voice conversations, adjust tone and language settings, and experience the low-latency performance that makes these voice agents feel responsive and human-like.

You'll then customize your conversational AI agent for practical business applications by building an airline customer support assistant. This involves tailoring the system prompt with specific context, testing different voice options, and observing how the AI agent uses provided information to answer questions accurately and assist with travel needs.

The lecture explores advanced features including the workflow canvas for connecting multiple conversational agents, template-based qualification flows that route conversations based on user intent, and the Knowledge Base functionality. You'll learn to add documents containing domain-specific information—demonstrated through an Apple products example—enabling your voice agent to deliver accurate responses with subject matter expertise using RAG (Retrieval-Augmented Generation) principles.

By the end, you'll understand how to deploy customizable, enterprise-grade voice agents in minutes, integrate APIs, automate workflows, and create AI-powered assistants for various use cases including customer service, telephony, and multilingual support scenarios.

If you want to learn:

How do I add custom tools to my ElevenLabs voice agent to connect with external platforms like n8n?

What are the built-in system tools available in ElevenLabs and how can they enhance my conversational AI agent?

How do I embed an ElevenLabs voice agent widget on my website using HTML and customize its appearance?

What authentication methods and security settings can I configure for my ElevenLabs conversational AI agent?

How do I set up agent-to-agent transfers and create multi-agent workflows in the ElevenLabs platform?

What advanced settings control my voice agent's behavior, including response timing and speech recognition features?

Then this lecture is for you!

This lecture provides a comprehensive walkthrough of essential ElevenLabs voice agent features, focusing on tools, widget deployment, and security configuration. You'll explore the Analysis section to review conversation history, then dive deep into the Tools feature where you'll learn to equip your AI agent with custom and system tools. Discover built-in tools like conversation control, automatic language detection, and the Transfer to Agent feature for creating multi-agent workflows. The lecture demonstrates how to customize your conversational AI widget, including configuring the orb avatar, uploading custom images, and generating embed codes for WordPress or any HTML-based website. You'll learn client-side deployment methods and how to share your widget across multiple platforms. The Security section covers authentication methods, user controls for text-only or voice interactions, webhook configuration for conversation tracking, and usage limits to prevent excessive API calls. Finally, explore Advanced settings including text-only agent mode, Scribe for automatic speech recognition, custom keyword optimization for product names, and behavioral parameters that control response timing, interruption sensitivity, and silence handling. This hands-on guide prepares you to build, customize, and deploy enterprise-grade conversational AI agents with the ElevenLabs platform.

If you want to learn:

How do I build my first ElevenLabs agent workflow with routing capabilities?

What are the steps to create a multi-agent voice AI system for customer service?

How can I set up specialized subagents with different knowledge bases in ElevenLabs?

How do I configure LLM conditions to route conversations between voice agents?

What's the difference between using system prompts and override prompts in agent workflows?

How do I deploy a conversational AI agent with handoff functionality?

Then this lecture is for you!

In this hands-on lecture, you'll build a complete ElevenLabs agent workflow from scratch using the Agent Workflows editor. You'll start by creating custom knowledge bases containing product information and stock data, then configure a multi-agent system with three specialized voice AI agents: a main routing agent, a Product Support specialist, and a Stock Specialist. You'll learn how to override system prompts for precise agent behavior, assign different voice settings to each subagent, and attach specific knowledge bases to control what information each agent can access. The lecture demonstrates how to set up LLM conditions on workflow edges to enable intelligent routing based on user intent, allowing seamless conversation flow between agents without requiring users to repeat questions. You'll see a live deployment and testing session where the voice agent successfully handles both product inquiries and stock availability questions by automatically transferring to the appropriate specialist agent. This practical deep dive into ElevenLabs agent workflows provides the foundation for building conversational AI systems with complex routing logic, preparing you to create sophisticated voice agents for real-world customer service use cases.

If you want to learn:

How do I integrate ElevenLabs with n8n for AI voice agents?

What are the two orchestration patterns for connecting ElevenLabs and n8n workflows?

Should n8n or ElevenLabs handle the orchestration in voice agent automation?

How do I reduce latency in AI voice agent conversations?

What's the difference between using n8n as the orchestrator versus ElevenLabs conversational AI?

How do webhooks and APIs work in workflow automation platforms?

Then this lecture is for you!

This lecture explores two distinct integration patterns for combining ElevenLabs conversational AI with n8n workflow automation. You'll discover the n8n-orchestrated approach, where n8n manages the end-to-end workflow and calls ElevenLabs API for text-to-speech (TTS) and speech-to-text (STT) capabilities. Then you'll learn the ElevenLabs-orchestrated pattern, where the ElevenLabs agent drives the conversation and uses tools to trigger n8n workflows for business logic. The lecture covers critical concepts including latency optimization in real-time AI voice agents, webhook configuration, HTTP requests (GET and POST methods), and API endpoints. You'll understand why the ElevenLabs-first approach delivers superior performance for voice interactions despite added complexity, leveraging ElevenLabs' low-latency voice capabilities and advanced features like telephone integration. The session includes practical explanations of how voice AI agents process audio in real-time, how to set up agent configuration with LLM integration, and when to use each orchestration pattern based on your use cases. You'll gain hands-on knowledge of workflow automation tools, conversational AI agents setup, and best practices for building context-aware, human-like voice assistants that connect multiple apps and services through n8n's automation platform.

If you want to learn:

How do I integrate ElevenLabs text-to-speech with n8n workflows?

What are generic nodes in n8n and when should I use them?

How do I set up ElevenLabs API credentials for AI voice automation?

What's the difference between HttpRequest nodes and Webhook nodes in n8n?

How can I automate AI voice generation using n8n and ElevenLabs?

How do I pass dynamic text from an AI agent to ElevenLabs for speech synthesis?

Then this lecture is for you!

This lecture covers the fundamentals of generic nodes in n8n and demonstrates how to build a complete text-to-speech workflow using ElevenLabs and n8n. You'll learn the distinction between platform-specific nodes and generic integration nodes, including the HttpRequest node for API calls and the Webhook node for incoming events. The tutorial provides step-by-step instructions for obtaining and configuring your ElevenLabs API key with proper credential setup and security permissions.

You'll discover how to create an n8n workflow that connects Google Gemini AI with ElevenLabs voice synthesis, learning to configure the AI agent node and pass dynamic output using expressions. The lecture demonstrates practical implementation of the ElevenLabs text-to-speech node, including voice selection, parameter configuration, and using JSON expressions to automate voice generation. You'll understand when to use tools versus workflow steps, how to handle API authentication, and troubleshooting techniques for testing connections.

By the end, you'll have built a fully automated AI-powered workflow that converts AI-generated text into lifelike audio using ElevenLabs, with the knowledge to integrate any third-party API into n8n using generic nodes for custom automation solutions.

If you want to learn:

- How do I create a voice webhook using n8n and ElevenLabs?

- What's the best way to integrate speech-to-text and text-to-speech in a workflow?

- How can I build a conversational AI voice agent without writing code?

- How do I set up webhook nodes in n8n to handle voice data?

- What are the steps to connect ElevenLabs API with n8n for voice automation?

- How do I create real-time voice workflows using AI and webhooks?

Then this lecture is for you!

In this hands-on lecture, you'll build a complete voice-enabled AI workflow using n8n, ElevenLabs, and speech-to-text technology. You'll start by configuring the ElevenLabs text-to-speech API to generate audio responses from AI agents, testing different voice profiles to find the perfect tone for your voice assistant. Next, you'll set up a webhook node in n8n to create an endpoint that receives audio input, then connect it to ElevenLabs speech-to-text service to transcribe voice messages into text. You'll learn how to route transcribed text through an AI agent for conversational responses, then convert those responses back to speech using the ElevenLabs API. The lecture covers essential webhook configuration, including switching from GET to POST requests, handling binary audio files, and using the respond_to_webhook node to return audio data to the caller. You'll also work with a simple HTML interface that records voice input in the browser and sends it to your n8n workflow automation endpoint. By the end, you'll understand how to orchestrate asynchronous voice workflows, troubleshoot common integration issues, and create scalable conversational AI agents using open-source workflow automation tools—all without writing a single line of code.

If you want to learn:

- How to build a voice agent using n8n workflow automation?

- How to integrate ElevenLabs voice AI with webhooks for real-time conversations?

- How to connect speech-to-text transcription with an AI agent in n8n?

- How to troubleshoot and fix common errors when building AI voice agents?

- How to create a conversational AI receptionist that responds with natural voice?

- How to use API calls to transform audio into text and back to speech in a workflow?

Then this lecture is for you!

This hands-on tutorial demonstrates how to build a functional AI voice agent using n8n workflow automation, webhooks, and the ElevenLabs API. You'll follow a step-by-step process where audio is captured from a web page, posted to an n8n webhook, transcribed into text using ElevenLabs conversational AI, processed through an AI agent powered by Gemini, and converted back to speech for real-time voice responses. The lecture covers practical troubleshooting of common integration errors, including fixing undefined properties and configuring node connections properly. You'll learn how to set up the complete workflow from webhook configuration to audio response handling, understand how to use expression evaluation for data transformation, and see the entire voice AI agent process in action. The tutorial also explores how this n8n workflow template can be extended with memory, tools, and embedded into applications like WordPress sites, providing a foundation for building more complex conversational AI systems with low-latency voice interactions.

If you want to learn:

How do I connect ElevenLabs voice agents to n8n workflows using webhooks?

What are the steps to build an AI voice agent that can query data from external sources?

How can I integrate ElevenLabs conversational AI with automation tools like n8n?

What is the process for creating custom tools in ElevenLabs that trigger n8n workflows?

How do I set up webhook communication between AI voice agents and workflow automation platforms?

What are the best practices for building voice-driven automation with ElevenLabs and n8n?

Then this lecture is for you!

In this hands-on lecture, you'll learn how to build a complete integration between ElevenLabs voice agents and n8n workflow automation using webhooks and custom tools. You'll start by creating an n8n workflow with a webhook trigger and configuring an AI agent powered by Gemini to interact with Google Sheets data. The lecture walks you through setting up the webhook node, implementing the AI agent with proper tools, and testing the workflow to ensure it retrieves information correctly.

Next, you'll configure a custom tool in ElevenLabs that enables your voice agent to communicate with n8n through HTTP POST requests. You'll learn how to define tool descriptions, set up webhook URLs, configure request bodies with proper parameters, and establish the connection between both platforms. The lecture demonstrates practical use cases like building an AI voice assistant that can answer questions about equity portfolios by querying data through automated workflows.

By the end of this session, you'll understand the complete workflow orchestration process, from webhook configuration and AI agent setup to tool creation and real-time voice-driven automation. This integration enables you to build scalable voice AI solutions that can interact with external data sources and automate complex tasks without code.

If you want to learn:

How do I connect ElevenLabs voice agents with n8n workflows using webhooks?

What's the best way to build a production-ready AI voice agent with custom tools?

How can I integrate conversational AI with automated workflows for real-time responses?

What are the steps to configure webhook tools in ElevenLabs to call external APIs?

How do I deploy a voice agent to production that can handle multiple questions?

What's the difference between using chat triggers and webhook nodes in n8n for voice agents?

Then this lecture is for you!

This hands-on tutorial demonstrates how to build a production voice agent by integrating ElevenLabs conversational AI with n8n workflow automation using webhooks. You'll learn the step-by-step process of configuring a custom webhook tool in ElevenLabs that calls an n8n workflow to retrieve real-time data from Google Sheets. The lecture covers troubleshooting common integration issues, properly configuring webhook nodes to capture JSON body parameters, and setting up the AI agent node to process voice queries. You'll discover how to structure POST requests with custom fields, connect ElevenLabs voice agents to external business logic, and deploy both platforms to production for seamless multi-turn conversations. The tutorial walks through the complete round-trip flow from voice input through webhook triggers to AI processing and back to voice output, demonstrating how to achieve lower latency responses compared to traditional chat-based approaches. By the end, you'll have a fully functional voice-driven assistant that can interact with your data sources and handle follow-up questions in real-time using no-code automation tools.

If you want to learn:

- What is RAG (Retrieval-Augmented Generation) and how does it work in AI systems?

- What's the difference between RAG and Agentic RAG, and when should you use each approach?

- How can you make AI agents and LLMs more knowledgeable without expensive training?

- What are the practical use cases for building RAG systems in enterprise AI solutions?

- How does retrieval work to augment large language models with external knowledge?

- What are the benefits of RAG for AI applications and generative AI models?

Then this lecture is for you!

This lecture demystifies Retrieval-Augmented Generation (RAG) and Agentic RAG, two transformative approaches in modern AI development. You'll discover how RAG works by dynamically retrieving relevant information from knowledge bases and data sources to augment LLM responses, making AI agents more knowledgeable without costly model training. The session explains the core difference between traditional RAG and Agentic RAG systems, showing how RAG focuses on retrieval and context injection while Agentic AI takes autonomous decision-making further. You'll learn the fundamental RAG architecture: how queries trigger retrieval from databases and vector databases, how retrieved data gets injected into prompts, and how this enables AI systems to provide accurate, real-time answers grounded in external knowledge rather than relying solely on static training data. The lecture covers practical use cases for enterprise AI, from building RAG-powered chatbots to AI assistant applications, and explains how RAG helps prevent hallucinations in generative AI models. You'll understand the RAG pipeline workflow, including how LLMs use APIs and tools to fetch relevant information from multiple data sources, and how Agentic RAG combines the dynamic data retrieval of RAG with the autonomy of agentic systems for advanced AI agent development. Perfect for those building AI solutions with LangChain or similar frameworks, this session provides the intuition needed to implement RAG systems and create more capable, knowledge-enhanced AI applications.

If you want to learn:

How do RAG systems use embedding models to enable smarter AI knowledge retrieval?

What are embedding models and how do they convert text into meaningful vectors?

How does semantic search differ from traditional keyword search in AI applications?

What makes embeddings capture semantic meaning better than simple text matching?

How can you implement vector search to find relevant information in your knowledge base?

Why are embedding models essential for building commercial AI agent systems?

Then this lecture is for you!

This lecture explores how embedding models power semantic search in retrieval-augmented generation (RAG) systems. You'll discover how embedding models—a specialized type of LLM also called encoders or vector embedding models—transform text into numerical representations that capture semantic meaning rather than just matching keywords. The lecture demonstrates why traditional keyword search fails when users ask questions using different terminology (like "Heathrow Airport" instead of "London") and how embeddings solve this brittleness through fuzzy, semantic search.

You'll learn the fundamental concept of how embedding models generate vectors—lists of numbers representing text meaning in multidimensional space—where semantically similar content produces vectors that are close together. The lecture explains how this proximity in vector space enables you to retrieve relevant information from your knowledge base even when query words don't exactly match your stored data. You'll understand how these embedding vectors work with vector databases to perform vector search, allowing LLMs to access contextually relevant information before generating responses.

The lecture covers practical applications for building commercial AI agents and generative AI solutions, explaining how embedding models enable advanced RAG implementations that go beyond simple text matching. You'll see how embeddings capture semantic relationships between different phrases with similar meanings, making your AI applications more robust and intelligent. This comprehensive guide provides the foundation for implementing semantic search systems that power modern AI applications, from chatbots to information retrieval systems, using embedding models to bridge the gap between user queries and your internal knowledge base.

If you want to learn:

How does retrieval augmented generation (RAG) actually work behind the scenes? What are vector databases and why are they essential for RAG systems? How do embeddings and semantic search enable LLMs to access real-time information? What's the difference between traditional RAG and agentic RAG architecture? How can you implement RAG to give your AI applications access to company knowledge bases?

Then this lecture is for you!

This lecture demystifies how RAG works by walking you through the complete RAG pipeline step-by-step. You'll discover how retrieval-augmented generation transforms user queries into vector embeddings using an embedding model, then performs semantic search within a vector database to retrieve relevant information. The lecture explains the RAG architecture in detail: how questions are vectorized, how vector databases store and query data based on vector similarity, and how retrieved context gets inserted into the LLM prompt to generate accurate responses. You'll learn why modern databases like PostgreSQL and MongoDB now support vector search, understand that the embedding model operates independently from the language model, and see how RAG provides real-time access to external knowledge without retraining. The lecture covers practical use cases for RAG including HR systems, customer support, and knowledge retrieval applications where LLMs need expertise about company products, policies, and data. You'll also get introduced to advanced RAG techniques like graphRAG, hierarchical RAG, and re-ranking, plus learn why RAG evaluation and measurement are critical for optimizing RAG systems. Finally, discover what makes agentic RAG different from traditional RAG approaches and how this RAG technology is transforming generative AI applications.

If you want to learn:

- What is the difference between traditional RAG and agentic RAG in AI systems?

- How do AI agents make smarter decisions in retrieval-augmented generation workflows?

- How can you integrate vector databases with n8n for advanced AI retrieval?

- What makes agentic RAG more adaptive than simple RAG pipelines?

- How do you use Supabase with n8n to build sophisticated AI workflows?

- Why should AI agents control the retrieval process instead of following linear workflows?

Then this lecture is for you!

This lecture explores the fundamental differences between traditional RAG and agentic RAG systems, demonstrating how agentic AI transforms static retrieval workflows into adaptive, multi-step processes. You'll discover how traditional RAG follows a linear pipeline—user query to vector-based retrieval to LLM response—while agentic RAG empowers AI agents to make intelligent decisions about retrieval strategies, choosing between vector search, SQL queries, and other tools to find the best context for answering questions.

The lecture covers the agentic approach to retrieval-augmented generation, where large language models control the workflow rather than simply generating responses. You'll learn how AI agents can access vector databases, execute semantic searches using vector similarity, and even perform traditional database queries when appropriate, making the retrieval process smarter and more efficient for complex tasks.

Additionally, this session introduces Supabase integration with n8n workflows, explaining how this PostgreSQL-based database platform stores vector embeddings and supports AI retrieval systems. You'll understand why Supabase is popular for building RAG pipelines, its generous free tier for AI projects, and how to set up your account for storing and querying vector data. The lecture prepares you for building an expert voice agent with complete knowledge base access, combining agentic RAG with automated data pipelines to create sophisticated AI systems that can handle enterprise AI use cases and conversational AI applications.

If you want to learn:

- How does Retrieval-Augmented Generation (RAG) actually work with vector databases?

- What is the difference between traditional RAG and agentic RAG systems?

- How do you build a complete data ingestion pipeline for AI applications?

- What are vector embeddings and how do they enable semantic search?

- How do you chunk documents effectively for vector storage?

- What are the two distinct phases of building production-ready RAG systems?

Then this lecture is for you!

This lecture provides a comprehensive deep dive into building RAG systems using Supabase vector database and pgvector. You'll master the fundamentals of Retrieval-Augmented Generation, understanding how vector embeddings transform text into searchable numerical representations for semantic search and similarity search operations.

The lecture covers the complete RAG architecture, breaking down the two critical phases: data ingestion pipelines and query retrieval workflows. You'll learn the extract, transform, and load (ETL) process specifically adapted for vector stores, including document chunking strategies, embedding generation using OpenAI models, and vectorization techniques that enable efficient vector search across large datasets.

You'll explore the evolution from traditional RAG to agentic RAG, where AI agents autonomously manage retrieval workflows using multiple tools and iterative approaches. The lecture demonstrates how Supabase, an open-source Postgres database built on top of pgvector, provides scalable vector storage capable of handling millions of embeddings with millisecond query performance.

Key technical concepts include vector similarity search, metadata integration, schema design for documents tables, and the practical implementation of RAG pipelines using n8n for workflow automation. You'll understand how embedding models (encoders) convert user queries into vectors, how HNSW indexes optimize retrieval speed, and why chunking strategies must be tested against your specific dataset and use cases.

The lecture also addresses common misconceptions about RAG being obsolete due to larger context windows, explaining why vector-based retrieval remains essential for scalable AI applications and efficient resource utilization in production environments.

If you want to learn:

How do I build a RAG pipeline using n8n and Supabase?

What's the best way to automate data ingestion from Google Sheets into a vector database?

How can I create an AI-powered expert system for my business using workflow automation?

What are the steps to set up Supabase vector store with n8n for retrieval-augmented generation?

How do I transform and load data into a vector database for AI chatbot applications?

What's the difference between basic chatbots and RAG systems for business automation?

Then this lecture is for you!

In this hands-on lecture, you'll build the data ingestion pipeline for a complete RAG system using n8n workflow automation and Supabase vector store. You'll learn how to extract product data from Google Sheets, transform it using the Edit Fields node in n8n, and load it into a Supabase PostgreSQL vector database for AI-powered question answering. This lecture covers the essential ETL process for RAG applications, showing you how to integrate n8n with Supabase using proper API credentials and authentication. You'll discover why Supabase is an enterprise-grade, scalable solution for vector storage and how to work with vector embeddings for retrieval-augmented generation. The workflow you build will handle 60 product records but is designed to scale to thousands of entries, making it perfect for real-world business applications. You'll also learn best practices for data transformation, understand the architecture of agentic RAG systems, and prepare your infrastructure for adding AI chat functionality. This practical tutorial focuses on building production-ready automation workflows that can be immediately implemented for clients, with clear explanations of each node configuration and integration setup in the n8n interface.

If you want to learn:

How do you map data from one format to another using n8n's Edit Fields node?

What's the best way to structure content for vector embeddings in a RAG system?

How do you set up a Supabase project for building AI-powered chatbots?

What are the essential steps to prepare data for retrieval-augmented generation workflows?

How can you transform product data into LLM-ready content using n8n workflow automation?

Then this lecture is for you!

In this hands-on tutorial, you'll master data mapping with n8n's Edit Fields node and set up your first Supabase project for building a RAG system. You'll learn how to transform raw product data into structured content optimized for vector embeddings and retrieval-augmented generation. The lecture walks you through manual mapping techniques, showing you how to create content fields that combine product names, categories, SKUs, prices, and descriptions into LLM-ready text. You'll discover how to use expressions like $JSON to dynamically pull data and structure it for AI agents and chatbots. The tutorial then guides you through creating a Supabase account, setting up an organization, and launching your first database project with pgvector support. You'll learn best practices for metadata tagging, including how to add category fields for filtering search results. By the end, you'll understand how to build data pipelines that prepare information for vector stores, execute workflow automation steps in n8n, and configure Supabase as your vector database backend. This practical session covers essential n8n workflow template patterns, database setup with PostgreSQL, and the foundational architecture needed for building agentic RAG systems with searchable knowledge bases.

If you want to learn:

How do I set up Supabase database tables for n8n RAG integration?

What is the correct database schema for storing vector embeddings in Supabase?

How do I configure PostgreSQL extensions for vector storage in Supabase?

What are embedding dimensions and why do they matter for RAG systems?

How do I create custom SQL functions for n8n's vector store operations?

What's the proper way to structure a knowledge base table for retrieval-augmented generation?

Then this lecture is for you!

In this hands-on lecture, you'll learn how to configure Supabase as a vector store for your n8n RAG workflow. You'll start by navigating the Supabase dashboard and understanding the project structure. The lecture walks you through enabling the vector extension in your PostgreSQL database, which is essential for storing embeddings and performing vector search operations.

You'll execute custom SQL code to create a knowledge_base table with the proper schema that n8n expects, including fields for id, content, metadata, and embedding vectors. The lecture explains how to set up the critical match_documents function that n8n uses to retrieve relevant context from your vector database during the RAG process.

A key focus is understanding embedding dimensions and why they must match your chosen embedding model. You'll learn why OpenAI's Embedding Small model uses 1,536 dimensions and how to configure your Supabase database accordingly. The lecture also covers alternative embedding options including Gemini and open-source models.

By the end, you'll have a fully configured Supabase vector database ready to store documents from Google Drive and support your AI agent's retrieval operations. You'll verify the successful table creation through the Supabase interface and prepare for the next step: connecting n8n to populate your knowledge base with automated file ingestion from Google Drive.

If you want to learn:

How do you connect n8n to Supabase vector store for AI-powered workflows?

What are the steps to configure OpenAI embeddings with Supabase in n8n?

How do you set up API credentials and authentication between n8n and Supabase?

What's the proper way to load and chunk data into a vector database using n8n?

How do you add metadata to your vector store for better semantic search results?

Then this lecture is for you!

This step-by-step tutorial walks you through the complete integration of n8n with Supabase vector store using OpenAI embeddings. You'll learn how to navigate Supabase project settings to locate your database URL and API keys, including the legacy service role key required for n8n authentication. The lecture demonstrates how to add and configure the Supabase vector store node in your n8n workflow, connect it with proper credentials, and set up the embeddings OpenAI node using the text-embedding-3-small model with 1,536 dimensions. You'll discover how to implement the default document loader to properly chunk and ingest text data into your vector database, configure the data loading process to target specific content fields, and add custom metadata properties like categories to enhance your semantic search capabilities. This tutorial provides practical guidance on building your own AI-powered RAG (retrieval-augmented generation) system by connecting these essential AI tools, ensuring your PostgreSQL pgvector setup matches your embedding dimensions, and establishing a solid foundation for workflow automation with vector search functionality.

If you want to learn:

- How do I run a complete data ingest pipeline using n8n and Supabase?

- What are the steps to load and vectorize data into a Supabase vector database?

- How can I build a RAG system pipeline that processes and stores embeddings automatically?

- How do I configure the Supabase vector store node in n8n workflows?

- What's the easiest way to transform data and create a knowledge base for retrieval-augmented generation?

- How do I troubleshoot and rerun my n8n workflow when fixing data errors?

Then this lecture is for you!

In this hands-on session, you'll execute a complete data ingest pipeline using n8n with Supabase to build a functional RAG system. You'll configure the Supabase vector store node by connecting it to your knowledge_base table, then run the workflow to process 60 items through extraction, transformation, chunking, and vectorization stages. Watch as your n8n workflow automatically generates embeddings using OpenAI and stores them in your Supabase vector database with proper metadata configuration. Learn to verify your data in the Supabase SQL editor, troubleshoot common issues like missing table parameters, and quickly rerun your pipeline to fix data errors. This practical guide to building a rag pipeline demonstrates the complete flow from empty database to populated vector store, showing you how to transform spreadsheet data into AI-ready embeddings. By the end, you'll have a working data ingest workflow that loads vectorized content into PostgreSQL, setting the foundation for your retrieval-augmented generation system. Perfect for anyone building AI agents, chatbots, or agentic RAG systems who wants step-by-step instruction on n8n and Supabase integration.

If you want to learn:

How to build a RAG-powered AI voice customer support agent that can answer questions about your business or products?

What are the key steps to integrate ElevenLabs voice agents with Supabase database and n8n workflow automation?

How does retrieval-augmented generation (RAG) work to give AI agents access to your knowledge base and provide accurate answers?

How to create an AI voice assistant that can handle real-time conversational queries using vector embeddings and database integration?

What tools and workflow configurations are needed to build AI voice agents with document retrieval capabilities?

Then this lecture is for you!

This lecture completes the RAG-powered AI voice agent project by building the question-answering component and integrating ElevenLabs voice capabilities. You'll learn how to create an n8n workflow that uses an AI agent to handle conversational queries by retrieving relevant information from your Supabase vector database. The lecture covers the complete RAG system architecture, including how vector embeddings work with OpenAI Embedding Small model to transform queries into 1,536-dimensional vectors for database lookup. You'll configure the AI agent with a chat trigger, integrate a Gemini chat model (or your preferred LLM), implement memory for natural conversation flow, and add RAG tools that enable the agent to search your knowledge base. The session demonstrates how to connect all components—the conversational AI assistant, the vector database with your indexed documents, and the voice interface through ElevenLabs—to create a production-ready AI voice customer support solution. You'll understand both phases of RAG implementation: the data ingest pipeline (extracting, transforming, chunking, and vectorizing documents) and the real-time query response system that provides context-aware, accurate answers to user questions.

If you want to learn:

How do you build an agentic RAG workflow in n8n that can handle thousands of documents?

What's the difference between a simple RAG system and an agentic RAG AI agent?

How do you connect Supabase vector store to n8n for intelligent data retrieval?

Why do you need embeddings when querying a vector database in a RAG system?

How can you create a production-ready RAG AI agent that scales from 60 to 600,000 products?

Then this lecture is for you!

In this hands-on lecture, you'll build a complete agentic RAG workflow in n8n using Supabase vector store. You'll learn how to configure the Supabase vector store as a tool for your AI agent, set up the "Retrieve Documents as Tool for AI Agent" operation, and write effective tool descriptions that guide your agent's behavior. The lecture demonstrates how to select the proper knowledge base table, configure result limits, and integrate OpenAI embeddings (text-embedding-3-small) to vectorize user queries for semantic search. You'll discover why embedding models are essential even after your data is already vectorized—because each user question must be converted to vectors for similarity matching. Through a live demonstration, you'll see the RAG system retrieve relevant product information, with the AI agent intelligently organizing and presenting results with prices and descriptions. This workflow in n8n showcases the true power of retrieval-augmented generation: the ability to scale from dozens to hundreds of thousands of documents without performance degradation. By the end, you'll understand how n8n's visual workflow builder makes creating production-ready agentic RAG workflows remarkably simple, setting the foundation for building more advanced AI-powered automation systems.

If you want to learn:

How do I integrate ElevenLabs voice AI agent with n8n using webhooks?

What's the difference between n8n-triggered and ElevenLabs-triggered integration patterns?

How do I set up a webhook node in n8n to receive POST requests from ElevenLabs?

What is the best way to connect ElevenLabs conversational AI with n8n workflow automation?

How do I configure an AI voice agent to call external workflows as tools?

What are HTTP methods like GET and POST, and why do they matter for webhook integration?

Then this lecture is for you!

This lecture demonstrates how to set up ElevenLabs voice AI agent integration with n8n using webhook-based architecture. You'll learn the superior integration pattern where ElevenLabs acts as the primary agent and treats your n8n workflow as a custom tool, enabling lower-latency voice interactions compared to n8n-triggered approaches.

The tutorial covers essential webhook configuration in n8n, including setting up a webhook node to receive POST requests, configuring the endpoint to accept JSON payload data with a question field from the body, and implementing a respond-to-webhook node to return processed results. You'll understand key API terminology including endpoints, HTTP methods (GET vs POST), and how webhooks function as reverse APIs that trigger workflow automation.

Step-by-step, you'll configure the AgenticRAG workflow to connect the webhook trigger with an AI agent node, modify chat input settings to accept webhook data using expressions like $json.body.question, and prepare the integration for ElevenLabs voice agent setup. This approach allows ElevenLabs to handle speech-to-text and text-to-speech conversion while simultaneously executing your n8n business logic, creating an efficient voice AI agent with custom tool functionality.

If you want to learn:

How to build a voice AI agent using ElevenLabs conversational AI without coding required?

How to connect ElevenLabs and n8n to create an automated sales assistant?

How to integrate webhook tools with your AI voice agent for real-time product lookups?

How to set up a conversational AI agent with custom system prompts and workflow automation?

How to deploy and test a voice AI agent that can handle customer inquiries seamlessly?

Then this lecture is for you!

In this hands-on tutorial, you'll build a fully functional voice AI agent for an electronics e-commerce store using ElevenLabs conversational AI and n8n workflow automation. You'll create an "Electronics E-commerce Sales Expert" agent from scratch, starting with configuring a custom system prompt that defines your AI agent's purpose and behavior. The lecture walks you through selecting and customizing voice settings, then demonstrates how to integrate a webhook tool that connects your voice AI agent to an n8n workflow for real-time product information retrieval.

You'll learn the step-by-step process of setting up webhook integration between ElevenLabs and n8n, including configuring POST methods, body parameters, and data types to enable your AI voice agent to ask questions and receive responses from your knowledge base. The tutorial covers essential setup details like execution modes, pre-tool speech configuration, and typing sound effects to create a more natural conversational experience.

The lecture demonstrates both testing and production deployment workflows, showing you how to transition from test URLs to production URLs, publish your agent, and generate shareable links. You'll see live testing of the voice AI agent handling customer inquiries about keyboards, with real-time visualization of the n8n workflow executing in the background. This no-code approach to building voice agents makes AI automation accessible for creating intelligent sales assistants that can seamlessly handle customer conversations and automate product inquiries.

If you want to learn:

• How to deploy AI voice agents to production using Twilio phone integration?

• How to connect ElevenLabs conversational AI voice agents with a real phone number?

• How to build a production-ready voice AI system that handles inbound and outbound calls?

• How to integrate Twilio voice with n8n workflow automation for real-time conversations?

• How to create a voice agent that uses RAG (Retrieval Augmented Generation) with Supabase and OpenAI embeddings?

• How to set up Twilio phone numbers and configure voice webhooks for AI-driven customer interactions?

Then this lecture is for you!

In this hands-on lecture, you'll deploy a fully functional AI voice agent to production using Twilio phone integration and ElevenLabs conversational AI. You'll learn how to set up a Twilio account, acquire a Twilio phone number, and configure voice webhooks to connect with your ElevenLabs agent. The tutorial shows you step-by-step how to import your Twilio number into ElevenLabs using your account SID and auth token from the Twilio console dashboard.

You'll witness a live demonstration of an AI voice agent handling real phone calls, answering product inquiries, and providing pricing information in natural conversations. The system integrates multiple technologies including n8n workflow automation, Gemini 2.5 Flash as the conversational model, OpenAI embeddings for vectorization, and Supabase for the knowledge base—all working together in real-time with low-latency responses.

The lecture covers the complete Twilio integration process, from navigating the Twilio dashboard to configuring the voice webhook and assigning your phone number to an AI agent. You'll see how the production-ready system handles inbound calls seamlessly, using text-to-speech and context-aware responses powered by RAG technology. This practical implementation demonstrates how to automate customer calls, create a support agent for appointment booking, or build use cases for service businesses looking to let your AI handle telephony interactions.

By the end, you'll understand how to combine Twilio voice, ElevenLabs agent capabilities, and n8n workflow orchestration to create AI-powered voice experiences that can transform customer interactions and automate higher-value work for businesses.

If you want to learn:

- Should I choose n8n cloud vs self-hosted for my automation needs?

- How do I set up n8n self-hosted on my local machine?

- What are the real differences between cloud vs self-hosted n8n deployment options?

- Is self-hosting n8n worth it compared to using n8n cloud?

- How does n8n pricing compare between cloud solution and self-hosted options?

- What are the best practices for deploying n8n on your own server?

Then this lecture is for you!

This lecture provides a comprehensive comparison of n8n cloud vs self-hosted deployment options to help you choose the best value for your automation platform needs. You'll discover the key differences between using the fully managed n8n cloud service and self-hosting n8n on your own infrastructure, including considerations for workflow execution, data control, and n8n pricing models.

The lecture covers the advantages of n8n cloud, including one-click deployment, fully managed services, simplified webhook handling, and easy OAuth integrations with platforms like Google Sheets and Gmail. You'll understand how the cloud service handles underlying infrastructure, managing servers, and automatic updates under the Fair Code license.

You'll also explore the benefits of n8n self-hosted deployment, including unlimited workflows, unlimited executions, complete control over your data, enhanced data security and privacy, and cost-effective operation of the n8n community edition. The lecture explains self-hosting options ranging from running n8n on your local machine using Docker to deploying n8n on a VPS with providers like Hetzner or DigitalOcean.

Key technical considerations covered include webhook configuration challenges with self-hosted instances, advanced OAuth 2.0 setup requirements, Docker deployment methods, reverse proxy configuration, and the differences between using n8n.io versus n8n on your own server. You'll learn about deployment options using Docker Compose, Kubernetes, and various cloud computing platforms for those ready to deploy n8n beyond local development.

The lecture provides practical guidance on choosing between n8n cloud's starter plan with 2.5k executions per month versus self-hosting for run unlimited workflows, helping you make an informed decision based on your automation needs, technical capabilities, resource usage requirements, and whether you prioritize convenience or data control for your workflow automation platform.

If you want to learn:

How do I install Docker Desktop on Windows and Mac?

What's the best way to run n8n locally on my computer?

Should I use Docker or NPM to install n8n?

How do I set up a self-hosted n8n instance step-by-step?

What are the prerequisites for running n8n with Docker?

How do I configure WSL2 for Docker on Windows?

Then this lecture is for you!

This comprehensive step-by-step tutorial walks you through installing Docker Desktop and setting up n8n locally on both Windows and Mac systems. You'll learn how to install Docker Desktop, configure WSL2 on Windows for optimal Docker performance, and understand why Docker is the recommended approach over NPM for self-hosting n8n. The lecture covers the complete Docker installation process, from downloading Docker Desktop to launching your first Docker container. You'll discover how to use PowerShell on Windows and Terminal on Mac to run essential commands, navigate the n8n documentation for self-hosting, and prepare your local environment for workflow automation. Whether you're on Windows with an Intel or ARM chip, or Mac with Apple Silicon or Intel processor, this tutorial provides platform-specific guidance to successfully install n8n locally. By the end, you'll have Docker Desktop running on your computer and be ready to deploy your local n8n instance for building powerful automation workflows without relying on n8n cloud services.

If you want to learn:

- How to install Docker Desktop on your computer and get started with containers?

- What Docker volumes are and how to create one for n8n workflow automation?

- How to run n8n locally using Docker with a complete step-by-step guide?

- What each part of the Docker run command does when setting up n8n?

- How to configure environment variables and timezone settings for your local n8n instance?

- How to verify your Docker container is running properly on Docker Desktop?

Then this lecture is for you!

In this hands-on tutorial, you'll learn how to set up n8n locally using Docker Desktop through a complete step-by-step process. The lecture walks you through the Docker Desktop interface, explaining containers, images, and volumes in simple terms. You'll discover how to create a dedicated Docker volume for n8n data storage using the terminal or PowerShell command line. The tutorial provides detailed instructions for running the docker run command to start your n8n container, including how to configure timezone settings, map network ports, and set environment variables. You'll learn what each flag in the Docker command does, from the -p port mapping to the -v volume configuration, and understand how Docker images work as blueprints for containers. By the end of this lecture, you'll have n8n running locally on your computer in an isolated Docker environment, ready for workflow automation. The tutorial covers both Mac and PC installations, addresses common troubleshooting issues, and explains best practices for self-hosting n8n with Docker.

If you want to learn:

- How do I run n8n with Docker on my computer?

- What happens when Docker downloads the n8n image for the first time?

- How do I access my self-hosted n8n instance after starting the container?

- Why do I see error messages about Python when starting n8n in Docker?

- How do I set up my n8n owner account on a local instance?

- What's the difference between localhost in Docker and localhost on my computer?

Then this lecture is for you!

In this hands-on lecture, you'll learn how to run n8n with Docker by executing your first Docker command and starting your n8n container. You'll watch the complete process of Docker downloading the n8n image from the registry when it's not found locally on your system, and understand what happens during the initial setup. The lecture walks you through interpreting Docker output messages, including migration reports and Python runner warnings that appear during container startup, explaining why these messages occur inside the container and why they don't affect your deployment.

You'll discover how to use Docker Desktop to verify your running n8n container, check the n8n_data volume for persistent data storage, and understand port mapping between your Docker container and host machine. The lecture demonstrates accessing your self-hosted n8n instance by navigating to localhost:5678 in your web browser, setting up your owner account with proper credentials, and exploring the n8n interface running locally on your computer. You'll learn the key difference between the container's internal localhost and your host machine's localhost, and how Docker maps port 5678 to enable browser access to your n8n instance. By the end, you'll have a fully functional self-hosted n8n workflow automation tool running in a Docker container with persistent storage configured.

If you want to learn:

- How to set up self-hosted n8n workflow automation on your computer using Docker?

- How to integrate OpenRouter with n8n to access advanced AI models like DeepSeek?

- How to create your first AI agent with chat capabilities and tool calling features?

- How to connect external APIs like MarketStack to your AI agent for real-time data access?

- What are the differences between using cloud-based AI models versus running Ollama locally?

- How to troubleshoot common issues with AI model integration and tool calling reliability?

Then this lecture is for you!

This lecture provides a comprehensive step-by-step guide to setting up a self-hosted n8n automation platform with AI-powered agents using OpenRouter and DeepSeek AI. You'll learn how to configure your n8n instance running in a Docker container, navigate the platform interface, and access key settings including version management and usage plans.

The tutorial walks you through creating your first workflow from scratch, starting with a chat message trigger and building an AI agent with memory capabilities. You'll integrate OpenRouter as your chat model provider using API key authentication, then configure DeepSeek v3.2 as your AI model to create an intelligent chatbot running entirely on your computer.

The lecture demonstrates how to enhance your AI agent by adding tools, specifically integrating the MarketStack API for real-time stock price data retrieval. You'll learn proper credential setup, parameter configuration, and how to enable filters for accurate data queries. The content covers troubleshooting tool calling issues with different models and explores alternatives like OpenAI's GPT o3s 120b model running through OpenRouter for more reliable performance.

You'll gain practical experience building AI-powered workflow automation that connects multiple apps and services, understanding the architecture of agents as LLMs equipped with tools to achieve specific goals. The lecture also discusses deployment options, including the differences between running Ollama locally versus using cloud-based solutions, and considerations for GPU acceleration on different operating systems.

If you want to learn:

How do I run n8n self-hosted on my local machine instead of using the cloud version?

What is Ollama and how can I use it to run AI models locally on my computer?

How do I integrate Ollama with n8n to create AI workflows using local LLMs?

What's the difference between connecting to APIs in n8n cloud versus self-hosted n8n?

How can I set up AI automation workflows that run completely locally without external API calls?

What are the steps to configure Docker for running n8n with Ollama integration?

Then this lecture is for you!

This lecture demonstrates how to run n8n self-hosted using Docker and integrate it with Ollama to execute AI workflows using local LLMs. You'll learn the practical differences between n8n cloud and self-hosted instances, particularly regarding credential setup for services like Google Sheets. The lecture walks through installing Ollama, downloading open-source models like Mistral and Gemma, and configuring the Ollama chat model node in n8n. You'll discover how to use Docker's host.docker.internal mapping to connect your n8n container to Ollama running on localhost port 11434. The demonstration includes building a functional AI agent workflow that uses local language models to answer queries and call tools, all running entirely on your local machine. You'll see real examples of model selection based on your computer's RAM and GPU capabilities, and understand the performance considerations when running local AI automation. This hands-on guide covers the complete setup process for self-hosted AI workflows, from Docker container configuration to testing AI-powered applications with locally deployed LLMs.

If you want to learn:

- How does OAuth 2.0 authentication work in n8n workflow automation?

- What's the difference between API calls and webhooks in workflow development?

- How do I set up advanced integrations with n8n Cloud?

- What are the best practices for organizing workflows using projects and folders?

- How can I configure webhook triggers and HTTP requests in n8n?

- What authentication methods should I use for different API integrations?

Then this lecture is for you!

This lecture covers advanced n8n workflow automation techniques, focusing on three authentication methods: simple API keys, one-click OAuth 2.0, and custom OAuth 2.0 client configuration. You'll learn the fundamental differences between API calls and webhooks, understanding how HTTP requests work as endpoints and how webhook nodes function as trigger mechanisms in your automation workflows.

The session provides hands-on guidance for transitioning to n8n Cloud for production workflow development, including setting up AI agents with OpenRouter and DeepSeek integration. You'll discover how to organize complex workflows using n8n's project management features, including creating projects, folders, and using sticky notes for visual workflow design.

Key technical concepts covered include HTTP methods (GET and POST), webhook triggers versus action nodes, JSON data transformation, and the HTTP request node for custom API workflows. You'll learn best practices for building scalable automation workflows, managing credentials across projects, and structuring your n8n workspace for commercial functionality. The lecture demonstrates practical workflow examples using chat models, AI agents, and memory configuration, preparing you to build production-ready automation solutions with proper authentication and integration patterns.

If you want to learn:

- How do I set up Google OAuth2 credentials for n8n workflows?

- What are the step-by-step instructions to configure the OAuth consent screen in Google Cloud Console?

- How do I create OAuth client ID and connect Google services to my n8n instance?

- What is the correct way to set up authorized redirect URIs for n8n Google integration?

- How can I enable Google Drive API and configure Google credentials in n8n?

- What are the prerequisites and best practices for Google OAuth2 authentication in workflow automation?

Then this lecture is for you!

This comprehensive step-by-step tutorial guides you through setting up Google OAuth2 credentials for n8n workflows. You'll learn how to create a Google Cloud project, navigate the Google Cloud Console, and configure the OAuth consent screen for your automation platform. The lecture covers enabling the Google Drive API, creating OAuth client ID and client secret, and properly configuring authorized redirect URIs to authenticate Google services in n8n.

You'll discover how to set up Google credentials in n8n by copying the OAuth redirect URL from the n8n credentials modal and pasting it into the Google Cloud Console. The tutorial walks you through selecting the correct user type (internal for Google Workspace or external for Gmail accounts), adding test users, and creating OAuth2 credentials that allow your n8n instance to access Google services like Google Drive, Google Sheets, and Gmail.

This guide emphasizes best practices for OAuth setup, including proper credential management and troubleshooting common authorization errors. By the end of this lecture, you'll have fully functional Google OAuth2 credentials configured in your n8n workflow automation platform, enabling powerful automation with Google services. Perfect for self-hosting users and anyone looking to integrate Google API authentication into their n8n workflows.

If you want to learn:

- How do I set up OAuth2 authentication for Google Drive in n8n?

- What is the easiest way to monitor new files uploaded to a Google Drive folder automatically?

- How can I receive push notifications when files are added to Google Drive?

- How do I create a workflow automation that triggers on Google Drive file changes?

- What's the difference between OAuth2 and API key authentication for Google Drive integration?

- How do I connect n8n to Google Drive and set up automated file monitoring?

Then this lecture is for you!

This hands-on tutorial walks you through the complete process of building an automated workflow that monitors a Google Drive folder for new files and sends push notifications using n8n and Pushover. You'll learn how to configure OAuth2 credentials to integrate Google Drive with n8n, understanding why OAuth2 provides more secure and flexible authentication compared to simple API keys. The lecture demonstrates step-by-step how to create a Google Drive trigger node that polls a specified folder every minute to detect when new files are uploaded, then connects this trigger to a Pushover notification node to send instant alerts. You'll see the entire OAuth2 authentication flow in action, from creating credentials in the Google Cloud Console to authorizing the connection and testing the workflow. The tutorial covers setting up the Google Drive trigger to watch for file creation events, configuring poll intervals, and publishing your workflow for live monitoring. By the end, you'll have a fully functional automation that detects new files in your Google Drive folder and delivers real-time push notifications to your device, with practical insights into workflow execution monitoring and debugging in n8n.

If you want to learn:

- How do I automatically extract text from PDF files uploaded to Google Drive?

- What's the easiest way to build a PDF extraction workflow using n8n?

- How can I automate data extraction from PDF documents without coding?

- Can I set up automatic notifications when PDFs are processed in Google Drive?

- What are the steps to create an n8n workflow for PDF text extraction?

- How do I connect Google Drive with n8n to extract information from PDF files?

Then this lecture is for you!

This hands-on lecture guides you through building a complete PDF text extraction workflow using n8n and Google Drive. You'll learn to set up a Google Drive trigger that monitors a specific folder for new file uploads, configure OAuth2 credentials for secure Google Drive integration, and automatically download files using the Google Drive node with expression-based file ID selection.

The workflow demonstrates how to use the Extract From File node to convert PDF documents into readable text format, process the extracted data, and send automatic notifications using Pushover. You'll follow a step-by-step process: creating a Google Drive trigger that polls every minute for changes, downloading files automatically when they arrive, extracting text content from PDF documents, and routing the extracted information to notification systems.

The lecture includes practical demonstrations of creating test PDF files, uploading them to monitored folders, executing workflows, and verifying successful text extraction. You'll also explore advanced concepts like implementing conditional logic with if statements to handle multiple file types, routing different document formats to appropriate extraction methods based on MIME types, and managing binary data within n8n workflows.

By the end of this session, you'll have a fully functional automation that saves hours of manual work by automatically processing PDF documents uploaded to Google Drive and extracting structured text content for further use in your workflows.

If you want to learn:

How to use Firecrawl with n8n for web scraping and data extraction?

What are structured outputs and why are they crucial for AI workflows?

How to integrate Firecrawl API into your n8n automation workflows?

How to convert unstructured LLM responses into structured JSON data?

How to build AI-powered web scraping workflows that extract LLM-ready data?

How to set up Firecrawl operations for search, scrape, and crawl functionality?

Then this lecture is for you!

This lecture demonstrates how to integrate Firecrawl's web scraping API with n8n to build intelligent data extraction workflows. You'll learn how to set up a Firecrawl account, obtain your API key, and install the Firecrawl node in your n8n instance. The lecture covers the essential concept of structured outputs—a powerful technique that forces AI agents to generate responses in a specific JSON format, making LLM outputs predictable and workflow-ready.

You'll build a practical automation that combines an AI agent with Firecrawl's search capabilities. The workflow uses structured output parsers to convert natural language questions into properly formatted search queries, which then feed into Firecrawl to scrape web data. You'll configure the AI agent with custom system prompts, implement the structured output parser with JSON templates, and connect the Firecrawl node to execute web searches based on AI-generated queries.

By the end of this lecture, you'll understand how to use Firecrawl to scrape data from any website, transform web content into LLM-ready markdown, and leverage structured data extraction for AI applications. You'll master the workflow automation techniques needed for modern web scraping, including how to handle API credentials, configure Firecrawl operations, and build reliable web scraping workflows that combine AI intelligence with powerful data extraction capabilities.

If you want to learn:

How to use the HTTP Request node in n8n to send data to external APIs and webhooks?

What are structured outputs and why are they crucial for workflow automation?

How to integrate webhook.site with n8n workflows for testing and debugging?

How to extract and transform JSON data from AI agents and send it to external systems?

What are the best practices for building complex workflows with authentication and data transformation?

Then this lecture is for you!

This comprehensive lecture demonstrates how to implement HTTP requests and webhooks in n8n workflow automation. You'll learn to use the HTTP Request node to make POST requests to external API endpoints, starting with webhook.site as a testing platform. The lecture covers structured outputs using the Output Parser with AI agents, showing how to configure DeepSeek through OpenRouter to generate JSON data that conforms to specific data structures. You'll discover how to integrate FireCrawl for web scraping and search functionality, then use the HTTP Request node to send JSON payloads to webhook URLs without writing custom code. The step-by-step guide includes authentication methods, node parameters configuration, and best practices for building automation workflows that process data from apps and services. You'll see how to connect an AI Agent with Simple Memory to a structured output parser, execute workflow logic that transforms data, and use webhook triggers to automate repetitive tasks. The lecture also demonstrates reading PDF files using Google Drive integration and extracting text content directly within the workflow. By the end, you'll understand how to design workflows that pull data from external systems, apply conditional logic, and trigger workflows based on JSON format responses—essential skills for creating no-code automation solutions.

If you want to learn:

- What is MCP (Model Context Protocol) and why is it being called the USB-C port for AI?

- How does MCP help AI agents and large language models connect to external tools?

- What makes MCP different from traditional AI integration methods?

- Why has MCP become such a widely adopted open standard in AI systems?

- How can you use MCP to connect AI applications to tools you didn't build yourself?

- What are the real-world use cases for MCP and how does MCP architecture actually work?

Then this lecture is for you!

This lecture provides a comprehensive introduction to the Model Context Protocol (MCP), an open standard that acts as a universal way for AI agents and large language models to connect with external tools and data sources. You'll discover why MCP is described as the USB-C port for AI tools, enabling seamless integration between AI systems and applications without custom coding for each connection.

The lecture clarifies the distinction between tool use in agentic AI (the fundamental innovation) and MCP (the standardized protocol that makes tool sharing easier). You'll learn how MCP provides a universal protocol for AI integration, allowing you to use tools that others have built and share your own tools with the AI community through this common protocol.

You'll explore MCP architecture and understand how MCP works as the bridge between AI applications and external systems. The lecture covers what MCP is and what it isn't, addressing common misconceptions about the protocol. You'll learn why MCP matters in the current AI landscape, how widespread adoption has made MCP the de facto standard, and what the future of MCP might hold.

The session also examines MCP integration within platforms like n8n, preparing you to build AI agents that can leverage the growing MCP ecosystem. You'll understand how MCP solves the challenge of connecting AI to multiple data sources and tools through a single, standardized approach, and why this open protocol has generated significant excitement in the AI community.

If you want to learn:

How does the Model Context Protocol architecture actually work with its Host, Client, and Server components?

What's the difference between using native n8n tools versus connecting to MCP servers through an MCP client?

How can you integrate external AI tools into your n8n workflow automation using MCP?

What are the three transport mechanisms (STDIO, SSE, and streamable HTTP) for connecting MCP clients and servers?

How do you turn your n8n workflows into MCP servers that other AI applications like Claude Desktop can use?

When should you use an MCP client tool in n8n versus building custom workflow nodes?

Then this lecture is for you!

This lecture breaks down the three-part MCP architecture: the MCP Host (your AI environment like n8n or Claude Desktop), the MCP Client (the connector component), and the MCP Server (the tool provider). You'll learn the three transport mechanisms for client-server communication—STDIO for local connections, deprecated SSE, and the modern streamable HTTP for remote integrations. The lecture demonstrates three practical ways to use MCP with n8n: adding an MCP client tool to your AI agent node for accessing external tools, creating an MCP server trigger to expose your n8n workflows as tools for other AI applications, and configuring global MCP server settings across multiple workflows. You'll understand when to use native n8n tools versus MCP client connections, how MCP standardizes tool integration across different workflow automation platforms, and why the Model Context Protocol solves the problem of connecting language models to external APIs and data sources. This technical deep-dive covers authentication methods, endpoint configuration, and best practices for integrating n8n with MCP servers, enabling you to extend your AI agent capabilities beyond built-in nodes using the open-source workflow automation platform.

If you want to learn:

- How to build an AI sales agent with n8n that automatically finds and qualifies prospects?

- What is MCP (Model Context Protocol) and when should you use it in your n8n workflows?

- How to use structured outputs to create consistent, reliable AI agent responses?

- What are the three ways to integrate MCP with n8n and which one is most practical?

- How to automate lead generation and qualification using AI-powered research?

- How to build a sales prospect finder that generates personalized outreach automatically?

Then this lecture is for you!

This lecture teaches you how to build an AI-powered sales prospect finder using MCP in n8n with structured outputs. You'll learn the three integration methods for MCP with n8n: using the MCP client node to connect to existing MCP servers, creating your own MCP server for others to use, and converting complete n8n workflows into MCP servers that Claude and other AI agents can call.

The tutorial covers practical implementation of structured output parsing to ensure your AI agent generates consistent JSON responses with prospect data including first name, last name, company, role, email, and qualification rationale. You'll discover why MCP is less critical in n8n compared to other platforms—because n8n already provides extensive native integrations—and when MCP becomes the right choice for your automation needs.

The step-by-step tutorial walks through configuring an AI agent with GPT-4o, setting max iterations to 30 for complex workflows, implementing structured output parsers, and designing JSON schemas for lead qualification. You'll learn to build a sales automation workflow that researches prospects, qualifies leads automatically, and generates personalized outreach—eliminating manual prospecting work for sales development representatives. This practical guide combines AI agent development, workflow automation, and lead generation into a fully automated, scalable sales pipeline.

If you want to learn:

How do I connect FireCrawl's MCP server to my n8n AI agent for web scraping?

What is the Model Context Protocol (MCP) and how does it work with n8n workflows?

How can I enable my AI agent to scrape websites and search the internet automatically?

What's the difference between using MCP tools versus traditional n8n nodes for web scraping?

How do I configure API credentials and environment variables for FireCrawl integration?

Why doesn't my LLM need manual instructions when using MCP server tools?

Then this lecture is for you!

This lecture demonstrates how to integrate FireCrawl's MCP server with your n8n AI agent to enable autonomous web scraping capabilities. You'll learn to configure the MCP client tool in n8n using HTTP streamable transport, set up your FireCrawl API key as an environment variable using $VARS, and connect to the remote hosted MCP server endpoint. The tutorial covers the complete workflow setup process, including adding the MCP client tool to your AI agent, configuring the system prompt for finding sales prospects, and understanding how the Model Context Protocol automatically communicates available tools and their capabilities to your LLM without manual prompt engineering. You'll discover why MCP integration is superior to traditional web scraping methods when you need your AI agent to make autonomous decisions about what to crawl. The lecture walks through the FireCrawl documentation, shows you how to structure the endpoint URL with embedded API credentials, and explains the difference between using core nodes versus MCP tools for workflow automation. By the end, you'll have a fully functional n8n workflow where your AI agent can independently use FireCrawl tools to scrape websites, search the internet, and extract structured data based on natural language queries—all without writing code or constant maintenance.

If you want to learn:

- How to build multi-agent AI systems that can use multiple tools simultaneously?

- How to integrate MCP servers with AI agents in n8n for real-world automation?

- How to connect Hunter.io API with MCP client for sales prospecting workflows?

- How to configure authentication and endpoints for streamable HTTP transport in MCP?

- How to create AI agents that automatically search, scrape, and find professional email addresses?

- How to structure JSON output from AI agent workflows using schema validation?

Then this lecture is for you!

In this step-by-step tutorial, you'll learn how to build a sophisticated multi-agent system in n8n using MCP client tool nodes and Hunter.io integration. You'll discover how to configure MCP servers with streamable HTTP transport, set up Bearer authentication for secure API connections, and create AI agents that can orchestrate multiple tools simultaneously. The lecture demonstrates a real-world sales prospecting workflow where an AI agent uses FireCrawl for web scraping and searching, then leverages Hunter.io's MCP server to find verified professional email addresses for potential clients. You'll see how the agent node intelligently routes between different MCP tools, making up to 13 API calls to complete complex tasks. Learn how to define system prompts that guide agent behavior, implement structured output parsers for JSON responses, and debug multi-agent workflows using n8n's visual workflow interface. By the end, you'll understand how Model Context Protocol enables AI agents to discover and use tools dynamically, how to manage credential systems for multiple external APIs, and how to build agentic automation that combines web research with CRM data enrichment for business applications.

If you want to learn:

- How to transform your n8n workflows into reusable MCP servers that other AI agents can access?

- What's the step-by-step process for exposing n8n workflows as MCP server endpoints?

- How to build a prospecting subagent using MCP integration with FireCrawl and Hunter.io?

- What's the difference between using MCP clients versus native n8n nodes in your automation workflows?

- How to configure workflow triggers and inputs to make your n8n instance callable by external MCP clients?

- What are the practical applications of packaging entire AI agent workflows as MCP tools?

Then this lecture is for you!

This hands-on tutorial demonstrates how to build your first n8n MCP server by converting an existing n8n workflow into an MCP server endpoint. You'll learn the step-by-step process of transforming a prospecting workflow—which uses FireCrawl MCP server for web searches and Hunter.io MCP client for email discovery—into a reusable tool that external AI agents can access. The lecture covers replacing chat triggers with "Execute Workflow" triggers, configuring workflow inputs using JSON parameters, and setting up the MCP Server Trigger node to expose n8n tools through a production URL. You'll discover how to use the Call n8n Workflow Tool to package entire automation pipelines as MCP tools, complete with proper descriptions and input configurations for AI agent discovery. The tutorial highlights practical DevOps considerations including when to use MCP integration versus native n8n nodes, how agentic AI makes autonomous decisions about tool usage, and the architecture of building subagents that can be called by larger multi-agent systems. By the end, you'll understand how to maintain full control over your automation platform while enabling external MCP clients to discover and execute your specialized n8n workflows through the Model Context Protocol.

If you want to learn:

- How to build and use MCP servers with n8n and Claude?

- How to integrate AI agents with external tools using the Model Context Protocol?

- How to create custom MCP servers that can be called by Claude and other AI applications?

- How to connect n8n workflows as MCP clients and servers for advanced automation?

- How to use MCP integration to access third-party tools not available in n8n?

- How to publish production-ready MCP server endpoints that AI models can discover and use?

Then this lecture is for you!

This lecture demonstrates how to build and deploy MCP servers using n8n workflow automation and integrate them with Claude AI. You'll learn how to configure n8n as an MCP client to connect to external MCP servers, enabling your AI agents to use third-party tools like Hunter and FireCrawl for sales prospecting. The tutorial covers creating a prospecting sub-agent workflow that leverages multiple MCP tools, then transforming that workflow into a custom MCP server using the MCP Server Trigger node. You'll see how to publish your n8n MCP server to production, generate an MCP server endpoint URL, and connect it to Claude Desktop as a custom connector. The lecture walks through a complete use case: building an AI-powered sales prospecting tool that finds consulting firm targets with verified email addresses. You'll learn how Claude can discover and invoke your custom MCP tools, how to troubleshoot MCP integration using execution logs, and how to orchestrate complex automation workflows where n8n functions as both an MCP client and server simultaneously. By the end, you'll understand the Model Context Protocol architecture, how to configure MCP connections, and how to extend AI capabilities by integrating n8n with Claude Code and other LLM applications through MCP endpoints.

If you want to learn:

- What is the Model Context Protocol (MCP) and how does it work as the "USB-C for AI apps"?

- How can you use MCP servers to connect AI agents to external tools like FireCrawl and Hunter.io in n8n?

- What's the difference between using AI agent tools versus structured outputs in your workflows?

- How do you build and share your own MCP server to make your n8n workflows available to other AI applications?

- When should you choose structured outputs over tool calls for building reliable AI workflows?

- How can you integrate MCP client nodes into your n8n automation platform for better AI agent functionality?

Then this lecture is for you!

This lecture recaps the Model Context Protocol implementation in n8n and guides you through the critical decision between structured outputs and tool use when building AI agents. You'll understand how MCP serves as an open-source standard connecting AI applications to external tools, with practical examples using FireCrawl and Hunter.io MCP servers. The session demonstrates two key MCP use cases: consuming third-party MCP tools through the MCP client node, and creating your own MCP server using the MCP server trigger node to share your n8n workflows with other AI systems like Claude. You'll learn the architectural difference between using tool calls (which give LLMs autonomous flexibility) versus structured outputs with JSON schema (which provide bulletproof reliability). The lecture emphasizes that structured outputs, enabled by the "require specific output format" parameter in the AI agent node, offer a more reliable approach for production AI workflows despite being less trendy than dynamic tool use. You'll see real examples of building an end-to-end prospecting sub-agent that uses MCP at multiple levels, and understand when to prioritize workflow reliability over agentic flexibility. The session concludes with the capstone project kickoff, preparing you to apply these MCP concepts and structured output techniques in building robust, production-ready AI automation workflows.

If you want to learn:

How does context engineering improve AI agent performance and reliability?

What is context engineering for AI agents and why does it matter?

How do you optimize prompt engineering and context windows for LLMs?

What are sub-agents and when should you use them in AI workflows?

How do you build production-ready AI agents using n8n?

What are the best practices for managing context in agent systems?

Then this lecture is for you!

This lecture provides a deep dive into context engineering and sub-agent architecture for building reliable AI agents. You'll learn how context engineering optimizes the information packed into an LLM's context window, including system prompts, conversation histories, RAG retrieval, tool descriptions, and structured outputs. The lecture covers context engineering strategies based on Phil Schmid's framework from Google DeepMind, explaining how to balance context window constraints with model coherence to achieve reliable AI system performance.

You'll discover how to implement sub-agents using n8n workflows to break complex tasks into independently testable steps. The lecture demonstrates practical approaches for dividing agentic problems into specialized agents, each with optimized context and focused tool sets. You'll learn when to use sub-workflows versus single agent architectures, understanding the trade-offs between autonomy and reliability in production AI systems.

Key topics include context optimization techniques, evaluation metrics for agent systems, context pruning strategies, and best practices for building production-ready agents. You'll explore how to avoid context poisoning, manage long-term memory and databases, and implement workflow automation that handles complex AI tasks. The lecture emphasizes experimentation and R&D approaches to effective context engineering, showing you how modern AI agent frameworks like n8n enable sophisticated multi-agent systems. You'll understand the critical balance between flexible, autonomous agents and bulletproof, reliable production systems that deliver consistent results for real-world AI applications.

If you want to learn:

- What is the lethal trifecta for AI agents and why does it pose a unique security risk to agentic AI systems?

- How can prompt injection attacks exploit AI agents that have access to private data and can communicate externally?

- What is the Agents Rule of Two and how does it help prevent data exfiltration in agentic AI security?

- How do you build strong agentic AI solutions that deliver accurate results instead of just plausible content?

- What are the anti-patterns to avoid when designing agentic LLM systems and workflows?

- How can you evaluate and test AI agent performance to ensure they solve real business problems?

Then this lecture is for you!

This lecture explores critical agentic AI security concepts, focusing on the lethal trifecta for AI agents—a unique vulnerability that occurs when an AI agent combines three characteristics: access to private data, ability to communicate externally, and exposure to untrusted content. You'll learn how prompt injection attacks can exploit this trifecta, using real-world examples like GitHub's MCP server vulnerability where malicious instructions in pull requests could potentially be used to steal sensitive data.

The lecture covers the Agents Rule of Two security principle and explains how untrusted content from sources like web scraping, MCP tools, or user prompts might contain malicious instructions that could trick your LLM into data exfiltration. You'll understand why combining tools and framework capabilities requires careful security operations and system design.

Beyond security, you'll discover what makes strong agentic solutions versus common anti-patterns. Learn why LLMs generate plausible content by design, and how your role as an AI engineer is to transform plausible outputs into accurate, measurable results. The lecture emphasizes identifying clear business problems, establishing success metrics before building, and implementing rigorous testing to ensure your agentic AI systems deliver real value rather than just generating convincing-sounding content. You'll learn to avoid the "human trap" of anthropomorphizing AI agents and instead focus on solving concrete business challenges with measurable outcomes.

If you want to learn:

How do I automate my sales pipeline to generate more business revenue?

What's the best way to integrate Pipedrive with n8n for CRM automation?

How can I build an automated outbound sales system using AI agents?

What are the steps to create a RevOps subagent for managing sales data?

How do I set up Pipedrive API integration for workflow automation?

What's the difference between leads, deals, and contacts in sales CRM systems?

Then this lecture is for you!

This lecture guides you through building an amplified automated sales pipeline using Pipedrive and n8n to solve the critical business problem of generating new sales. You'll learn to construct a multi-agent system featuring a Business Development Manager coordinating three specialized subagents: a Prospecting agent for lead generation, a RevOps subagent for CRM data management, and an SDR agent for outreach and lead nurturing.

The tutorial covers getting started with Pipedrive, a sales-focused CRM platform with free API access, including account setup, removing sample data, and obtaining your API key for integration. You'll discover how to navigate Pipedrive's interface to manage leads, deals, and contacts effectively.

The core focus is building the RevOps subagent in n8n—a workflow automation tool that streamlines your sales process by automatically creating structured records (persons, companies, and leads) in Pipedrive. This automation eliminates manual data entry, reduces human error, and creates a scalable sales system. You'll learn best practices for organizing subagents to optimize context usage and enable reusability across different workflows, making this solution adaptable for AI automation agencies, side projects, or enterprise sales teams looking to automate tasks and improve sales efficiency.

If you want to learn:

- When should you use structured outputs versus tools in AI workflow automation?

- How do you integrate Pipedrive with n8n to automate lead creation?

- What's the best way to pass data between workflow nodes in n8n?

- How can you use AI agents to parse unstructured data into structured JSON?

- Why do structured output parsers work better than tools for sequential workflows?

- How do you connect multiple Pipedrive operations in a single n8n workflow?

Then this lecture is for you!

This lecture demonstrates how to build a production-grade Pipedrive integration using n8n workflow automation with AI-powered structured outputs. You'll learn why structured output parsers outperform tools when creating sequential workflows that require data to flow between nodes. The tutorial walks through configuring an AI agent with OpenAI (GPT-4o or compatible LLM) to parse unstructured lead information into valid JSON format, then automatically create organization, person, and lead records in Pipedrive using the HTTP request node and Pipedrive API. You'll discover how to use the structured output parser to extract lead data (name, company, role, email) from natural language input, set up Pipedrive API credentials in n8n, and chain multiple workflow nodes together by passing IDs between operations. The lecture covers best practices for workflow execution, including how to reference data from prior nodes using drag-and-drop expressions, when to disable nodes for testing, and why workflow builders like n8n provide better error handling and maintainability than relying on LLM tool calls for sequential operations. This step-by-step guide is ideal for building scalable, low-code automation processes that integrate AI with CRM systems and external tools.

If you want to learn:

- How to build AI sales agents with n8n workflow automation?

- How to create an automated lead management system using Pipedrive integration?

- How to build an AI SDR agent that drafts personalized outreach emails automatically?

- How to use structured outputs versus AI tools for different automation workflows?

- How to integrate Gmail and Pipedrive CRM for sales automation on autopilot?

- How to eliminate manual tasks and streamline workflows for your sales team?

Then this lecture is for you!

In this step-by-step tutorial, you'll build two powerful AI sales agents using n8n workflow automation. First, you'll create a RevOps sub-agent that uses structured outputs to automatically create contacts, organizations, and leads in Pipedrive CRM with guaranteed reliability. You'll learn how to use OpenAI integration with strict workflow automation to ensure data flows seamlessly into your sales-focused CRM.

Next, you'll build an AI SDR (Sales Development Representative) agent that autonomously reads person records from Pipedrive and generates personalized outreach emails. This AI agent uses tools instead of structured outputs, giving it flexibility to retrieve CRM data and create draft emails in Gmail automatically. You'll discover how to craft effective system prompts that prevent AI hallucination and ensure professional, accurate communication.

The tutorial covers critical concepts including the "lethal trifecta" of AI automation safety, proper prompt engineering techniques, and how to choose between structured workflows versus autonomous AI tools. You'll see real workflow executions, learn how to integrate multiple APIs (Pipedrive and Gmail), and understand how to build sales automation that runs on autopilot while maintaining human oversight. By the end, you'll have two working sub-agents that automate lead enrichment and outreach, helping your sales process eliminate manual tasks and boost response rates.

If you want to learn:

How do you build a complete AI sales agent with n8n that automates lead generation and qualification?

What are the best practices for implementing sub-agents in your AI workflow automation?

How can you integrate AI-powered sales automation with CRM platforms like Pipedrive?

What is context engineering and why is it critical for building effective AI agents?

How do you transform manual sales processes into scalable, automated workflows using n8n?

What are the common pitfalls to avoid when building AI sales agents for B2B lead generation?

Then this lecture is for you!

In this capstone finale, you'll complete the Business Development Manager Agent by integrating three sub-agents into a unified AI sales automation workflow. You'll learn how to convert sub-workflows into production-ready agents using n8n's "When executed by another workflow" trigger, properly configure input schemas for seamless data flow, and implement best practices like sticky notes for workflow documentation. The lecture covers critical context engineering principles, including when to use sub-agents versus giving your AI agent full autonomy, and how to avoid the "human trap" of over-architecting agent solutions. You'll transform the SDR sub-agent and RevOps sub-agent from manual triggers to automated sub-workflows that handle lead qualification, draft email generation, and Pipedrive CRM integration. This step-by-step tutorial demonstrates how to structure AI agents with clear business metrics, rigorous testing protocols, and scalable automation that generates qualified leads automatically. You'll master the technical implementation of publishing workflows, defining input data modes, and connecting AI-powered agents that automate lead enrichment and outreach—creating a complete platform for B2B lead generation that eliminates time-consuming manual processes and delivers data-driven results.

If you want to learn:

How to build an AI sales agent with n8n that automates lead generation from start to finish?

What's the step-by-step process to create an AI-powered Business Development Manager workflow?

How to automate lead qualification and CRM integration using n8n workflows and AI agents?

What tools and techniques can help you build a scalable B2B sales automation system?

How to connect multiple AI sub-agents to handle prospecting, lead enrichment, and outreach automatically?

Then this lecture is for you!

In this hands-on tutorial, you'll build a complete AI Business Development Manager using n8n workflows that automates your entire sales pipeline. You'll create an intelligent system triggered by dropping an ICP (Ideal Customer Profile) file into Google Drive, which automatically extracts the data and orchestrates three specialized AI sub-agents. The workflow integrates a prospecting agent that searches the internet for qualified leads and predicts email addresses, a RevOps agent that saves lead information directly into Pipedrive CRM with proper data structure, and an SDR agent that generates personalized outreach emails. You'll learn how to configure the AI agent with OpenAI's GPT model, set up n8n workflow tools for each sub-agent, write effective tool descriptions for AI orchestration, and implement automated lead generation and qualification logic. This case study demonstrates practical B2B sales automation, showing you how to connect Google Drive triggers, PDF extraction nodes, and multiple workflow tools into one cohesive AI-powered system that eliminates manual, time-consuming sales tasks while maintaining personalization and data-driven decision making.

If you want to learn:

- How to build a multi-agent AI system that automates business development from lead generation to email outreach?

- How to orchestrate multiple AI agents in n8n to work together on complex workflows?

- How to integrate AI agent tools with real-world platforms like Pipedrive CRM, Gmail, and web scraping services?

- How to implement agent handoffs and coordinate specialized agents for prospecting, data management, and sales outreach?

- How to debug and troubleshoot multi-agent workflows when things don't work as expected?

- How to create autonomous AI systems that can handle end-to-end business processes with minimal human intervention?

Then this lecture is for you!

In this hands-on lecture, you'll build a complete multi-agent business development system using n8n workflow automation. You'll configure an orchestrator agent that coordinates three specialized sub-agents: a Prospecting Agent that searches for leads using Firecrawl and Hunter.io, a RevOps Agent that stores prospect information in Pipedrive CRM, and an SDL Agent that drafts personalized outbound sales emails in Gmail.

You'll learn how to write effective system prompts for AI agent orchestration, implement structured output parsing for reliable agent responses, and set up proper agent-to-agent handoffs. The lecture covers real-world debugging techniques, showing you how to troubleshoot common issues like incorrect field mappings, Boolean validation errors, and missing data in agent workflows.

You'll see how to integrate multiple platforms including Google Drive for file triggers, PDF extraction nodes, Pipedrive API for CRM operations, Gmail for email automation, and Pushover for notifications. By the end, you'll have a production-ready autonomous AI system that processes ideal customer profiles, discovers qualified leads, populates your CRM database, and generates ready-to-send sales emails—all without manual intervention. This complete guide demonstrates practical multi-agent system architecture, error handling strategies, and workflow automation best practices for building real-world agentic AI applications.

If you want to learn:

How do you build an AI agent that automatically records sales deals in Pipedrive?

What's the best way to integrate n8n with Pipedrive for CRM automation?

How can you use structured outputs with AI agents to create reliable workflows?

What tools do you need to automate your sales pipeline with artificial intelligence?

How do you set up webhook triggers for AI agent workflows in n8n?

Then this lecture is for you!

In this step-by-step tutorial, you'll build an Account Executive AI agent using n8n that automatically records deals in Pipedrive. You'll learn how to create a Deal Recording Sub-Agent that uses the OpenAI chat model (GPT-4) to identify customers in your Pipedrive database and create deal records when prospects express interest. The workflow demonstrates how to integrate Pipedrive with n8n AI agents using both tools and structured outputs for maximum reliability. You'll configure the agent to retrieve people from Pipedrive, use structured output parsing to validate customer data with four key fields (found, ID, company, and name), and automatically create deals based on the AI's response. The tutorial covers setting up conditional logic with if nodes, using expressions to handle JSON output, associating deals with person IDs, and converting the workflow into a webhook-triggered sub-agent that can be called by other workflows. You'll also implement push notifications to track workflow execution and learn best practices for balancing AI tools with structured outputs in production automation. By the end, you'll have a fully functional AI sales agent that streamlines your sales pipeline and automates CRM tasks in Pipedrive.

If you want to learn:

How do I integrate Google Calendar with an AI agent in n8n?

How can I build an automated booking system that checks availability and schedules demos?

What's the best way to create an AI scheduling agent that protects private calendar data?

How do I use n8n workflow templates to automate calendar bookings with OpenAI?

How can I build a demo booking agent that handles appointment scheduling automatically?

What are the steps to create an AI-powered calendar integration using n8n and GPT?

Then this lecture is for you!

In this comprehensive step-by-step tutorial, you'll build a fully functional demo booking sub-agent using n8n workflow automation and Google Calendar integration. Learn how to configure an AI agent with OpenAI GPT that intelligently checks calendar availability and automatically creates booking appointments. This hands-on tutorial shows you how to set up Google Calendar credentials using OAuth 2, implement two essential tools for checking availability and creating events, and protect sensitive calendar data while exposing booking functionality. You'll discover how to structure AI agent prompts with system messages, parse outputs into structured formats, and handle success or failure scenarios with conditional logic. The workflow includes webhook triggers for integration with other systems, respond nodes for real-time feedback, and business logic to ensure reliable booking automation. By the end, you'll have a working AI scheduling agent that can negotiate time slots, verify availability within business hours, and generate calendar events with location details and summaries—all while maintaining professional standards and data security for your booking systems.

If you want to learn:

How do you build a voice AI agent that can handle inbound sales calls automatically?

How can you connect ElevenLabs conversational AI voice agents with n8n workflow automation?

What's the best way to integrate voice agents with your CRM and calendar systems?

How do you configure agent prompts and tools for real-time customer interactions?

Can AI voice agents actually schedule demos and record deals without human intervention?

Then this lecture is for you!

This lecture demonstrates how to build a fully functional AI voice agent Account Executive using ElevenLabs and n8n workflow automation. You'll learn to create a conversational AI agent that handles inbound sales calls, collects caller information, records deals in Pipedrive CRM, and schedules demo appointments in Google Calendar—all in real-time.

The tutorial covers the complete setup process: configuring the ElevenLabs agent with a strategic system prompt, integrating two webhook-based tools (deal recording and demo booking), and connecting your n8n workflows to the voice agent. You'll see how to configure agent prompt parameters, set up body properties for name and time slot data, and connect a phone number to make your AI voice agent live and operational.

This hands-on session shows you how to let your AI voice agents automate the entire account executive workflow—from initial contact through deal creation and appointment scheduling. You'll learn troubleshooting techniques, proper webhook integration between ElevenLabs and n8n, and how to configure tools that enable your voice AI agent to interact with multiple systems simultaneously. By the end, you'll have a working voice agent that can handle real prospect calls and automatically log interactions in your CRM while booking meetings on your calendar.

If you want to learn:

How to successfully deploy a complete AI agent system that handles real business tasks automatically?

What does it take to build AI agents with n8n that can manage CRM deals, schedule demos, and interact with customers through voice?

How can you create a full AI automation workflow that integrates multiple tools like Pipedrive, Google Calendar, and ElevenLabs?

What are the key steps to building an AI automation agency using no-code platforms and AI-powered voice agents?

How to transform weeks of development work into hours using n8n AI agents and workflow automation?

Then this lecture is for you!

In this comprehensive course wrap-up, you'll witness a live demonstration of a fully functional AI agent system built with n8n that automatically handles customer calls, creates CRM deals in Pipedrive, and schedules demo appointments in Google Calendar. You'll see the complete architecture featuring two main AI agents—a business development manager and account executive—supported by five sub-agents working across six external integrations and seven LLM calls. This step-by-step tutorial reveals how to build AI agents with n8n and ElevenLabs that deliver measurable business impact in hours instead of months. You'll learn workflow automation techniques for integrating AI capabilities across multiple platforms, understand how to deploy AI solutions that process both structured and unstructured data, and discover how to create an AI automation agency offering. The lecture covers the entire three-week journey from foundational automation concepts through advanced topics like RAG workflows, MCP integration, context engineering, and sub-agents. You'll gain professional insights on testing and evaluating AI agent effectiveness, extending workflows for email automation and Slack integration, and building automated sales engines. Whether you're looking to automate repetitive tasks for your business, integrate AI into existing workflows, or offer AI automation services to clients, this hands-on demonstration shows you exactly how n8n AI agents and voice automation can transform your business processes and unlock new revenue opportunities.