The archive
Every ai & engineering essay we have published, newest first. Free to read, with no paywall at the end.
8 Sept 2026•5 min read
The jump from answering questions to operating software breaks most of the assumptions we built our AI features on. Here is what actually needs to change in your stack.
6 Sept 2026•4 min read
Automatic memoization removed a whole category of busywork from React codebases. It also exposed which of our performance habits were cargo cult all along.
5 Sept 2026•4 min read
Most RAG systems fail long before the embedding model is at fault. The fixes live in chunking, freshness, and permissions, not in a better index.
3 Sept 2026•3 min read
Sending every request to your largest model is the most expensive default in modern software. A routing layer usually beats an upgrade, on both cost and latency.
2 Sept 2026•3 min read
Reversibility is the cheapest trust mechanism available to anyone shipping automation, and it is consistently the last thing teams build.
1 Sept 2026•3 min read
Most codebases stop at typed function signatures and call it type safety. The value is in the boundaries: the network, the database, and everything a user can type.
30 Aug 2026•3 min read
Models change every few weeks. Prompts get rewritten by whoever touched them last. The only durable asset in an AI product is the set of cases you can test against.
29 Aug 2026•3 min read
When work takes ninety seconds, HTTP request-response stops being an adequate model. The patterns that fix it are borrowed from job systems, not from web frameworks.
27 Aug 2026•3 min read
You cannot filter your way out of untrusted text reaching a model. What you can do is make sure that text has no authority when it arrives.
26 Aug 2026•3 min read
Traditional logs answer what happened. With probabilistic components you also need to answer why this run differed from the last one, which requires capturing inputs you probably are not storing.
You've reached the end.
