Back home
Writing
Notes on GenAI systems
Field notes from shipping, updated with 2025-2026 ecosystem signals.
01
Reliability-first LLM systems: what actually works in production
How I design evals, fallbacks, and release guardrails for systems that survive real traffic.
02Context engineering playbook I use before touching prompts
The practical method I follow to shape inputs, retrieval, and constraints so outputs stay stable.
03Agentic workflows at scale: from demo loops to dependable systems
What changes when your agent needs to survive hundreds of tool calls and still produce trustworthy outcomes.
Want a topic covered sooner?
Send a note and I will prioritize it.