News for hackers. Stuff that matters.

A comment on If AI is mission-critical for your business, build your own feedback loop.

Re:If AI is mission-critical for your business, build your o... by anatolecallies on Wednesday February 25, 2026 @10:07AM (#47152533)
We run an LLM system that reads messy medical records and determines clinical trial eligibility.

We tried eval platforms, LLM-as-judge, and automated prompt optimizers. None helped with what actually mattered: hidden domain policies that weren’t explicitly written anywhere.

We ended up building our own annotation UI, prompt integration workflow (via Claude Code SDK), and HTML diff-based experiment reports.

The biggest lesson: off-the-shelves Eval/Annotations/Prompt Optimization tools are sub-part because they can only be generic.

Curious whether others building AI products have reached the same conclusion.

[ Parent | on HN ]
Re:If AI is mission-critical for your business, build your o... by consumer451 on Wednesday February 25, 2026 @10:25AM (#47152788)
I will be dealing with something along these lines next month. Thanks for sharing. I already had Opus build me an OLTP compatible tracing system, which took all of 4 hours, with annotations and experiments.
[ Parent | on HN ]