Agent evals in practice
A pragmatic way to test tool use, retrieval and failure handling before production.
Read more// Journal
Notes from the build
Practical notes on AI systems, architecture and cloud-native delivery.
// Journal
Practical notes on AI systems, architecture and cloud-native delivery.
A pragmatic way to test tool use, retrieval and failure handling before production.
Read moreThe questions we ask before adding distributed-systems complexity.
Read moreA clear-eyed guide to latency, deployment and the limits of the edge.
Read more