Not 'it feels better'. Fourteen questions better, two worse.
Every custom agent gets its own set of questions. A new version answers them beside the live version. The reviewer decides with a scorecard in front of them, not on a good feeling.
You ask the assistant you already use.
Datahub is headless: benchmarks too are reachable over MCP. You start a comparison and read the outcome in Copilot, Claude, ChatGPT or another assistant.
The same questions. Two versions. A fair judge.
A change to an agent starts as a draft, is reviewed and only then goes live. A benchmark adds evidence to that path.
Tested as the people who will use it.
An agent's answer depends on what it may see. So a benchmark runs the way the agent will really run.
The scorecard advises. People decide.
When an author submits a new version, the benchmark runs on its own. The scorecard appears in the review. No version is blocked by a number, because the owners know things no score captures.
The live version keeps answering while the new one is weighed.
An auditor can explain why a version went live.
Each run records who ran it, under which role, which versions were compared and which judge decided. Teams dare to improve more often, because every change is set against the same questions.
Who, which role, which versions, which judge.
What reviewers want to know.
Better agents. And the proof that they are better.
An intro call looks at which agent in your organisation deserves its own set of questions first.