Insights

What we've learned building this.

Notes on the parts of AI engineering that decide whether a feature survives contact with real users. Opinionated, and specific enough to argue with.

Product designEvaluationArchitecture RSS
Latest

Product design

5 min read

Design for the model being wrong

Every LLM feature fails sometimes. The difference between a product people trust and one they abandon is entirely in what happens next.

Read it

More reading

Follow along

New writing lands here as we hit problems worth documenting. No newsletter, no signup form — just a feed you can put in whatever reader you already use.

Subscribe via RSS

Working through one of these?

If you're making these decisions on a real product and want a second opinion, we're happy to talk it through — whether or not it turns into a project.

You can also read how we workfor how this thinking shows up in an actual engagement.

Start a conversation