Agentic AI Cohort — Build an AI-Powered App

Master agentic workflows by shipping a real app

Build "Budget Whisperer" — an AI-powered agent application with function calling, a Telegram bot, a web dashboard, and full deployment. 6 weeks, hands-on, project-based.

Price: €2,000 · Duration: 6 weeks · Format: Group cohort · Next start: April 6, 2026

Who is this for?

Intermediate Python developers who want practical LLM and agent patterns — not just API wrappers. You should be comfortable with Python, CLI tools, and Git. You'll learn structured outputs, function calling, prompt engineering, and how to build testable, deployable AI applications.

Time commitment: ~10 hours per week.

Program overview

Agentic AI program mindmap

What you build, week by week

Week 1

Scaffolding

  • Environment setup
  • Repository pattern
  • SQLModel entities
  • Python StrEnum
  • In-memory data layer
Week 2

Assistant Setup

  • Python Protocols
  • Type aliases
  • Pydantic structured outputs
  • OpenAI function calling
  • LLM client abstraction
Week 3

Tools for the Agent

  • Prompt engineering
  • Service layer pattern
  • CLI with Typer + Rich
  • Database repositories
  • Classification service
Week 4

Telegram Integration

  • Input preprocessing
  • Conversation handlers
  • Human-in-the-loop (HITL)
  • Inline keyboards
  • Telegram bot interface
Week 5

Web Interface

  • FastAPI fundamentals
  • Pydantic schemas
  • Streamlit dashboard
  • API integration
  • REST API + Web UI
Week 6

Deploy + Docs

  • Docker fundamentals
  • CI/CD pipelines
  • Test coverage (95%+)
  • Documentation
  • Production-ready agent

Tech stack: SQLModel, Pydantic, OpenAI function calling, Typer + Rich, FastAPI, Streamlit, Telegram bot API, Docker, CI/CD

What's included

  • Weekly group call with your coach
  • Code review via GitHub PRs — detailed, honest feedback
  • Professional, portfolio-ready project on GitHub
  • Structured 6-week curriculum
  • Access to invite-only community

Juanjo's coaching in action

Juanjo has coached developers 1:1 on AI projects before launching this cohort:

"In 6 weeks I built a full RAG pipeline — PDF ingestion, vector embeddings, and an LLM query layer that returns cited answers. The most surprising thing? It's not a huge technical challenge in Python. Even if you consider yourself a beginner, it's completely within reach."

— Tim G. · Built AI-powered search for QuietLinks

Your coach

Juan José Expósito González

Juan José Expósito González — Python & AI Mentor and PhD Engineer. Guides developers from Python basics to advanced AI implementations. Expert in Python, machine learning, blockchain, and algorithmic trading. Passionate about transforming complex concepts into practical, clean architecture, testable and deployable solutions.

Frequently asked questions

What community support is there? You get access to our invite-only community where you can ask questions, share progress, and connect with other developers.

Do I need AI/ML experience? No prior AI experience needed. You should be comfortable with Python — intermediate level. We teach the AI patterns through the project.

What if I fall behind? Sessions are recorded. You have async support from Juanjo and the group throughout the week.

Do I need an OpenAI API key? Yes, you'll use the OpenAI API for function calling and structured outputs. Cost is minimal (a few dollars for the full program).

Will this help my portfolio? Yes — an AI-powered app with agent tools, a Telegram bot, a web dashboard, and 95%+ test coverage is a strong portfolio piece. Employers are looking for developers who can build real AI applications, not just prompt wrappers.

How do I get started? Book a free intake call → and we'll talk about whether this is the right fit.

Ready to build AI applications that actually work? Book a free intake call →

Running a dev team? This cohort is a great way to upskill 5–10 developers together — get in touch for team pricing.