AI Agents For All! Build No-Code AI Agents & Master AI 2026

Design and build an AI interview coach that acts like a recruiter, using a memory block, calculator, and search API to practice, get feedback, and stay confident.

Explore an overview of Flowise, focusing on chat flows and credentials, explains free vs starter plans, cloud-based deployment options, and building a single agent with tools, templates, and marketplace access.

Build your first AI agent by configuring a conversational agent with memory and tools, compare conversational chain versus chain, and test using Serp API credentials for real results.

Discover how to use GPT-5 variants, including nano and mini, for no-code AI agents, compare API versions, tools, and web search capabilities, guided by thorough documentation.

Discover how the system message sets who the AI is and how it should talk. Learn how wording and framing steer decisions and guide role plays, templates, and tool use.

Build an ai interviewer agent guided by a system message, gather job details, research the company and interviewer, and propose and practice ten tailored questions with feedback.

This lecture guides you through finding a job, detailing how to define a title like entrepreneur in residence, research the company and interviewer, and prepare interview questions.

Explore completing the ai workflow by blending human-guided prompts with autonomous ai decisions, using a system message, one-by-one questions, and actionable feedback to prepare interview materials and test apps.

Add a calculator tool to your AI agent and deploy multi-tool workflows to handle math tasks, illustrated by a piano tuner estimation that demonstrates math checks and calculator use.

Explore how transformer architectures convert raw text into tokens via tokenization in LLMs. See how model-dependent tokenization differs and why embeddings, not token values, drive meaning.

Explore how to hide or reveal the system message in AI apps, balancing trade secrets and memory of previous messages, through a Harry Potter themed six-level game and cursor IDE.

Learn how temperature and top-p sampling control ai creativity and safety, moving from predictable results at low values to diverse, humorous outputs at higher settings.

Experiment with temperature and top p to balance creativity and determinism while playing rock paper scissors and rolling the dice, and learn how these parameters shape ai workflows and outputs.

Learn to build no-code AI service agents with Flowise for RAG, creating a digital waiter that fetches menu answers, calculates bills, and operates 24/7.

Discover retrieval augmented generation (rag) to keep answers up to date without retraining, cite sources, and tailor responses across domains by pulling relevant data, augmenting prompts, and generating grounded answers.

Create a GitHub account, sign in or sign up with Google, and create a new public repository named flow wise to explore no-code workflows and deployment options with render.

Explore deploying Flowwise on Render as a no-code AI agent solution, fork Flowwise, set up a web service with environment variables, and manage free-tier constraints and troubleshooting.

Avoid data loss on render's free plan by completing the practical videos in one session, as deployments can disappear when you return.

Build a no-code ai agent with memory and chat flow using an OpenAI model and document stores. Upload an Excel file, load with a document loader, and learn about chunks.

Master chunking to optimize ai agents by splitting large documents into small, context-rich chunks, avoid lost-in-the-middle, and apply long rag methods for faster, accurate answers.

Learn to set up document loaders for no-code AI agents by uploading restaurant data, previewing chunks, and configuring recursive text splitting with overlaps to create embeddings.

Embeddings translate words into numbers so machines can analyze text and find meaning. They place related words near each other, powering search, recommendations, chatbots, and document answering.

Set up embeddings by configuring OpenAI embeddings, adding API credentials, and exploring vector stores to compare data and query embeddings for fast retrieval with cost-aware pricing.

Discover how vector stores organize embeddings into a memory-like map to search by meaning, enabling AI to retrieve relevant data and answer from your own files.

Prepare a vector store using Pinecone, create and configure embeddings and indices, resolve dimension mismatches, and test retrieval to build AI features.

Set up and manage your database for AI agents by configuring upserts, handling updates from 43 to 86 chunks, and cleaning old content with a SQLite document store.

Discover how to build no-code AI agents without SQLite by using Supabase Postgres credentials with render or cloud flow wise, including setting up projects, record managers, and upsert.

Finish the ai agent by configuring chat flow, memory, and tools such as the retrieval tool and vector-store retriever. Show how to share the chat bot and display source documents.

Explore no-code ai agent projects, from an onboarding bot to a multi-channel agent that summarizes and suggests replies across Gmail, Discord, and Slack.

Learn to build a Flowise AI team acting as a mini product team with project manager, researcher agent, and designer agent, delegating tasks and enabling inter-agent loops.

This lecture introduces building an agent-based workflow by configuring a project manager agent to coordinate workers, use memory and JSON outputs, and drive tasks to achieve user goals.

Explore how to delegate tasks within an AI agent team using a flow state and conditions, with worker roles like researcher, ensuring clear input and seamless information flow through delegation.

Build and configure a researcher agent within the project manager workflow, using system messages and prompts to compare competitors, report highlights and lowlights, and apply structured reasoning.

The lecture demonstrates looping between a researcher and a project manager to build a restaurant menu management system, identify competitors and pricing, and manage delegation to prevent endless loops.

Finalize the project manager by defining roles—product designer, product manager, and head of product—and establish delegation flows using user stories, defining features, and prioritization.

As an expert product designer, you critique and improve AI design features by analyzing usability, aesthetics, accessibility, and functionality, with actionable recommendations.

As head of product, communicate the team's output to the user and prioritize features and user stories, presenting a prioritized list with rationale and next steps.

Explore no-code AI workflows for building a restaurant menu management interface, including collapsible menus, live previews, theming, accessibility checks, and delegation between project manager, designer, and product leads.

Provide feedback to turbocharge this course by sharing what's firing you up and what's missing the mark in the next lecture's feedback form.

Join the Manus waitlist, sign up with Google, and use an invitation code to earn free credits as you gain early access.

Learn prompt engineering for AI agents, define goals and tools, and apply plan, test, guardrails, and assets to drive SEO results and reliable product delivery.

Explore Manus, a no-code generalist autonomous AI agent that plans, assigns subagents, and uses memory caching with safety rails to deliver results.

Analyze a startup website to identify top five SEO keywords that boost awareness, then craft a practical, iterative plan to rank for those keywords using AI-driven insights.

Explore practical prompt engineering for autonomous AI agents, using outcome-first goals, context, guardrails, and checkpoints, plus tactics like one goal per prompt, clear deliverables, and self-checks.

Develop a comprehensive seo plan by analyzing top competitors, targeting primary and long-tail keywords, and outlining on-page and technical optimization for content creation.

Automate basic website testing by simulating sign-up, filling fields, handling otp verification, and exploring account creation constraints.

Explore no-code testing by creating a dummy restaurant named cafe, validating mandatory fields and plan selection, and verifying the creation in the management interface.

Build a no-code workflow to create a menu category and add an item for Eye Cafe, testing prompts, translations, and reliability while exploring automation and user interface challenges.

Test the no-code menu app by validating save and publish and mandatory fields. Translate categories and items across German, English, and French using the translations tab.

Apply chain of thought prompting to guide language models through intermediate reasoning for better multi-step solving. Use prompt engineering with clear instructions and context to turn models into experts.