T3-R5 ecosystem

Open app View repo

p95: A point on the slow tail: about 95 of 100 samples are faster.

JSON schema

Rubrics

Regression tests

The same job-shape-test card works for chat, voice, and a tool result.

The capstone reuses this card.

Write the goal in one sentence.

Name the input and the allowed output.

Save the trace next to the result.

The answer looks fluent and is wrong. Check whether a source passage actually contains the claim.

The loop never stops. Set a step cap and stop when the tool result repeats.