Skip to content

Track 06 · Applied AI · Build & Ship

Build cutting-edge things. Run them on your phone. Ship them.

The track that turns the systems knowledge into working products. Every lesson has a runnable artifact — most work in a Colab tab open on your phone. By the end you've built a RAG agent, a voice assistant, an on-device LLM, and shipped a capstone.

Modules in this track

  • Talking to LLMs — prompting, structured output, tool use, embeddings
  • RAG & Agents — retrieval, ReAct loops, multi-agent, MCP servers
  • Serve & Ship — vLLM, on-device inference, cost optimization, observability
  • Frontier & Capstone — multimodal, voice, safety, ship a production RAG-agent

What you’ll build

By the end of this track, your repo has:

  • A 3-tool function-calling assistant (Claude API, Colab notebook)
  • A RAG over 200 arXiv papers (hybrid search + cross-encoder reranker)
  • A ReAct agent solving SWE-style tasks (80 lines, no LangChain)
  • A 4-bit quantized LLM running on your phone via llama.cpp
  • A real-time voice agent (Whisper → Claude → Kokoro TTS)
  • A production-grade RAG-agent deployed to Vercel/Modal with eval suite + Langfuse tracing

Each lesson links to a runnable Colab so you can hit the API or run the model on your phone’s browser. No setup beyond opening a tab.