About the Program
What we teach, what we expect, and why we built it this way.
What This Program Is
The AI Developer Bootcamp is a hands-on, project-driven program for developers with Python experience who want to build production-style LLM-powered applications.
Rather than isolated exercises, students incrementally build a single evolving AI system. Each course adds new capabilities, patterns, and constraints — mirroring how real-world AI systems grow over time.
By completion, students produce a portfolio-ready AI application demonstrating:
- Grounded LLM usage
- Safety and guardrails
- Retrieval-augmented generation (RAG)
- Agentic behavior and tool use
- Cost, latency, and reliability considerations
What This Program Is Not
This program does not aim to:
- Teach ML model training
- Provide deep math or theory
- Optimize for viral demos
It focuses on applied LLM engineering in production-style systems.
Student Expectations
Students are expected to:
- Have baseline Python proficiency
- Act as self-directed developers
- Understand all code they submit
- Engage with feedback via GitHub PRs
How We Communicate
Most teacher–student communication happens in Slack. When you enroll, you’ll be added to a shared Slack workspace where you can:
- Ask questions anytime — no need to wait for scheduled sessions
- Get guidance from mentors on architecture, debugging, and design decisions
- Connect with other students working through the same challenges
Code feedback is delivered through GitHub PRs. Slack is for everything else — quick questions, sharing wins, getting unstuck.
Student Demos
At periodic checkpoints throughout the program, you’ll get the chance to demo your work to industry professionals — walking through what you built, the decisions you made, and what you’d do differently. It’s optional, but it’s great practice for explaining your system the way you would in a real interview or team standup.
Use of AI Tools
AI coding tools (ChatGPT, Copilot, etc.) are allowed, with strict expectations:
- Generated code must be understood
- Blind copy/paste is not acceptable
- Students remain accountable for correctness
Collaboration
- Discussion and collaboration are encouraged
- Direct copying without understanding is prohibited
- Respectful, professional interaction is required
Feedback Loop
- Work is reviewed via Pull Requests
- Feedback is delivered as inline code review
- Students revise until standards are met
This mirrors real-world engineering workflows.
Design Principles
The program is intentionally designed to emphasize:
Realism over shortcuts
Constraints over demos
Systems thinking over one-off prompts
Safety and reliability alongside capability
Students are not optimizing for novelty. They are optimizing for deployable reasoning systems.
Sound like a fit?
If you’re a self-directed developer who wants to build real AI systems — not watch videos about them — we’d like to hear from you.