LLM Digest
Subscribe

Story

hackernews_ai · Oct 29, 2026 · news

Source brief

Show HN: Apgar – Catch agent regressions without an LLM judge

github.comOct 29, 2026
original source linked

In brief

Hey HN, We build financial AI agents, and Apgar is the tool we wrote to see whether a harness change made an agent better or worse in production. Our offline evals can't cover every kind of question or session real us...

Feed lens
agentharnesseval

Continue reading

Read the original at github.com →Open in live feed

Earlier in this thread 4 items