Blog

Notes from the studio

Field notes on RAG, agents, and the path from pilot to production. Written for people who ship systems, not slide decks.

Operations

1–2 of 2

Operations

LLM Cost Control in Production: Routing, Caching, and Limits

Demo traffic is cheap. Production traffic is not. Routing, caching, and hard limits that keep quality inside a real budget.

10 min
Operations

Observability for AI Agents: Traces, Tool Calls, and Incidents

An agent looped for forty minutes and nobody saw it. Instrument traces, tool calls, and failure modes before users do.

10 min
Blog | Production AI Engineering Notes | Neurocell