Writes about shipping AI features in production
4 articles3 sections16 topics
Covers the distance between a working prototype and a system real users depend on — retrieval pipeline design, streaming and interruption handling, cost and latency budgeting, evaluation harnesses, and the error paths that decide whether a feature is trusted. Tutorials in this section are written to be run end to end.
This is a sample editorial profile shipped with the site. It carries no invented credentials, employers or social accounts, and will be replaced with a real contributor before publication.
Build a tool-calling agent as a Next.js route handler: typed tool definitions, a bounded loop, a streamed step log, and a client leaf that renders progress.
RAG solves a knowledge problem; agents solve an action problem. Where each architecture belongs, how they combine, and why their failure modes barely overlap.
The layers between a working AI demo and a system people depend on: call boundaries, budgets, tenant isolation, evaluation, observability, degradation.
How to stream model output into a React app without turning the page into a client bundle: Suspense boundaries, a tiny leaf, cancellation and stable layout.