Resources · Changelog
What shipped this week
Product updates across testing, evaluation and comparison.
v1.43 — Release verdicts
Compare now returns an explicit safe-to-release call.
v1.42 — Capabilities import
Import policies, tools, knowledge and workflows on the agent.
v1.41 — Regression matrix
Per-version PASS/FAIL columns across the suite.
v1.40 — Failure explorer
Two-column investigation view with the tool trace.
Test what your agent actually does
Connect an agent, generate scenarios and find the failures before your customers do.