Practical engineering notes on building production-grade AI systems — written for engineers, not for the hype cycle.
Building the loop that survives production: observe → decide → act → check → repeat, the patterns that extend it, and the boundaries that keep an agent inside its lane.
Read the series →Retrieval past the toy example: chunking that holds up, retrieval that returns the right thing, and the failure modes that only show up once real documents are involved.
Read the complete series →How tools actually connect to models: where the seams are, how authority and scope are decided, and what it takes to wire it up without surprises.
Read the complete series →