Resources

A curated map for learning agentic AI systems, LLM engineering, RAG, and the production habits that make AI features reliable.

Coding

Practical implementation notes for AI apps, backend systems, testing, observability, and production code quality.

Open Coding

Deep Dives

Longer technical explorations of agents, RAG, evaluation, reliability, and production AI tradeoffs.

Open Deep Dives

Suggested Learning Path

  1. 1Start with the core LLM engineering foundations.
  2. 2Add retrieval once your system needs private or fast-changing knowledge.
  3. 3Introduce agents only when the workflow needs tools, decisions, or multiple steps.
  4. 4Measure quality, latency, and cost before expanding the surface area.

Read the field notes

Explore practical posts on AI engineering, agents, evaluation, and system design.

Browse Posts