Pick a track
The map shows the whole terrain and topics group it by subject. A track is the third view: a curated route to a specific goal, built on the same dependency graph so nothing lands before what it needs.
- AI Literacy16 articles · ~17.5h
PMs, managers, and the curious — no coding
Understand what AI is, how it works, and where it fails — without writing a line of code.
- How AI Works36 articles · ~46.3h
Students and the theoretically minded
Build a real mental model of a transformer, from a single neuron up to attention.
- LLM App Developer24 articles · ~29.8h
Full-stack and product developers
Ship a product on top of the LLM API — prompting, evaluation, cost, and reliability.
- RAG Engineer15 articles · ~22h
Engineers building retrieval-augmented systems
Master retrieval augmentation end to end, from a basic pipeline to graph and agentic RAG.
- Agent Engineer16 articles · ~24h
Engineers building tool-using agents
Build agents that reason, call tools, and stay reliable across many steps.
- Applied ML20 articles · ~27.8h
ML engineers training and adapting models
Fine-tune, align, compress, and understand the architectures behind modern models.
- AI Safety & Security8 articles · ~10.8h
Security and compliance engineers
Defend AI systems: injection, jailbreaks, red-teaming, data handling, and governance.
- Production & Ops10 articles · ~13.3h
MLOps and platform engineers
Run AI at scale: serving, observability, cost control, and safe iteration.