2026 Bootcamp: Understand and Build Professional AI Agents

Discover practical tips to optimize your bootcamp experience and learn the secret to success: take personal responsibility, as you are the main key to your own progress.

Learn practical tips for bootcamp students, emphasizing practice over passive study and personal commitment to progress. Find your own system, practice discipline, and leverage social accountability to stay motivated.

Embrace hard work over magic pills, use negative feedback as motivation, and write your quitting fears plus a completion plan to stay committed.

Compile bootcamp 1 contents with the state of the generative ai revolution, including programming intro, a unicorn startup case on ai agents, and crew ai projects.

Choose the right learning path and pace in this introductory section of the 2025 bootcamp. Learn generative AI basics and its business impact, then advance to practical projects.

Explore building professional AI agents with Crew AI through multi-agent projects, using GPT-4 and llama 3.3, flows, and tools for email management and marketing project planning.

Learn to build professional level AI agents with Landgraaf, exploring memory, memory persistence, multi-agent systems, and human-in-the-loop workflows for enterprise use.

Explain why bootcamp two includes the intro to programming from bootcamp one, and show that programming and programming languages are accessible for beginners with generative AI tools.

Learn practical tips for people who have never programmed, introducing tools like virtual environments, terminals, secret credential files, and notebooks. See attached materials for detailed information.

Gain practical guidance for absolute beginners as you learn essential tools—virtual environments, terminals, secret credential files, and notebooks—and access attached materials for detailed coverage.

Use ChatGPT for daily learning, problem solving, and code review to accelerate your programming. Consult documentation and forums when needed, practice Python basics in Jupyter notebooks, and cultivate perseverance.

Explore how to use W3Schools for Python basics and leverage ChatGPT-4 as a personal programming assistant, from debugging and code generation to explanations and translations.

Explore the essential parts of Python and JavaScript for lm app development, including syntax, data types, functions, classes, modules, inheritance, and debugging, with attached notebooks and a summary presentation.

Master only the essential python and javascript concepts for building llm apps, focusing on practical syntax, data types, functions, classes, modules, and debugging with ChatGPT as a coding buddy.

Explore the virtual environment, understand what it is, why it matters for AI engineers, and learn how to create one.

Discover how virtual environments encapsulate Python versions and modules to prevent contamination and conflicts, and learn to create and activate them using pi env, pyenv, Anaconda or Miniconda.

Create a virtual environment and install Jupyter Lab to access, open, and create notebooks within the Jupyter Lab framework.

Create and activate a new virtual environment, install JupyterLab, and run a local JupyterLab server to manage notebooks and organize projects.

Explore the terminal, define what it is, why it matters, and perform basic operations. Review attached materials and note topics on hidden files and secret credentials in LLM applications.

Learn six daily terminal operations, including ls, cd, pwd, and pip install, to navigate directories, open a Jupyter Notebook, and install modules with confidence.

Explore hidden files for secret credentials, why secret files matter in language model applications, and how to create a secret credentials file.

Create and read hybrid notebooks that combine code and text in Jupyter notebooks, explore basic operations, and use ChatGPT for help while installing and experimenting with the notebooks.

Master Jupyter notebooks for code and markdown, create new notebooks, run and insert cells, and troubleshoot errors with ChatGPT guidance.

Explore why bootcamp #1 contents on AI agents and development platforms matter, including multi-agent concepts and our diagnostic thoughts on development alternatives at that time.

Compare traditional LM applications with modern AI agents, show real examples, outline current use cases, and preview near-future trends in AI agents.

Explore agentic artificial intelligence, compare traditional large language model apps with agentic workflows, review real-world examples like Klarna and Devin, and examine four usage patterns and near-term trends.

Explore multi-agent lm applications, assess promising initial results, and review Autogen, LangGraph, and CrewAI, along with other related initiatives.

Discover multi-agent LM applications where product manager, developer, and testing engineer agents collaborate to outperform single agents, and compare AutoGen, LangGraph, and Crew AI for scalable, simple frameworks.

Explore bootcamp two crew eye lessons, including an introduction to crew eye, setup guidance, and tips for using crew with grog and an alternative lms, plus a full stack project.

Explore Crew AI from the founders' perspective, learning why they built the framework and how to design multi-agent LLM applications, with use cases like replacing a human resources recruiter.

Explore CrewAI, an open-source LangChain framework to build multi-agent LLM applications. Design around a conceptual understanding of agent networks, keep two levels, and focus on marketing and sales use cases.

Explore crew ai in depth, configuring a multi-agent application and selecting an LM model. Set up dot env file, import tools, create agents and tasks, run the crew with input.

Explore crew AI and multi-agent architectures that handle fuzzy inputs, memory types (short-term, long-term, entity), tool use, delegation, and guardrails to plan, coordinate, and execute complex AI tasks.

Explore building a basic multi-agent LLM app using CrewAI, with hands-on steps, code from GitHub, and notebooks, all using Visual Studio Code.

Download the bootcamp code, install packages with poetry, and open notebooks in JupyterLab and VS Code; learn why poetry locks versions for stable projects.

Explore a step by step build of a multi-agent large language model app with CrewAI, replicating Lang Graph workflows, defining agents and tasks, and running end to end with poetry.

Explore the crew eye lessons in bootcamp two, including an introduction and initial guide to the platform, plus a full stack project, while noting bootcamp one content may be obsolete.

Discover a low-cost crew ai option using Grok with Llama3 and Mixtral, open-source LM models for multi-agent applications, with a free API key, pricing, notebook, and GitHub code.

Explore a low-cost multi-agent ai option using crew ai with grok, llama 3, and Mistral, contrasting with OpenAI's token-heavy pricing.

Explore the crew eye platform with an introduction, starter guide, alternative LMS tips, and initial full-stack projects, while noting bootcamp two adds new features and updates.

Explore building a level three crew ai multi-agent lm full-stack app across nine parts. Follow step-by-step guidance from project definition to front and back end, with notebooks.

Explore building a full stack multi-agent llm app with CrewAI, using a Flask backend and Next.js frontend, tested with Postman and organized with Poetry and pyproject.toml.

Define a technology research crew class to instantiate a new multi-agent crew for every user request, and implement an event-logging system with a dataclass-based log manager.

design a full stack multi-agent llm app with crewai part 3, logging kickoff and crew events while defining a two-agent crew: a research manager and a research agent.

Wire agents in cruise.py, define two research tasks in task.py, and emit JSON outputs using the business area info list model defined with pydantic.

Complete the backend of a multi-agent LLM app by wiring tasks, setting up crew with list comprehension, and integrating API endpoints and tools like YouTube search and online search.

Launch the Next.js front end for a multi-agent llm app with CrewAI, setting up a Tailwind css and TypeScript-based user interface with a header and layout, running on localhost:3000.

In part seven, this lecture deepens React basics by building the input section component and a home component that manages dynamic lists with useState in a Next.js frontend.

Dive into React for a full-stack multi-agent LLM app, building an event log and a final output component that shows technologies, blog articles, and YouTube videos.

Explore a complete, working full-stack multi-agent large-language-model app for customer service powered by crew AI, with a live events log, react hooks, and links to blogs and videos.