EvalGate Quality Evidence Agent

Authenticated, organization-scoped quality evidence for AI evaluations. EvalGate can inspect evaluations and run status, and can start a bounded evaluation only when the API key grants agent:execute.

Skills

• Inspect evaluations
  List evaluations visible to the authenticated organization without exposing repository files, credentials, or customer data from another organization.
  evaluationqualityread-only
• Inspect evaluation run status
  Read the status and aggregate result counts for one organization-scoped evaluation run.
  evaluationrunstatus
• Start a bounded evaluation
  Start an existing evaluation in dev or staging. This operation requires agent:execute and never creates, mutates, or deletes repositories, credentials, billing, prompts, or evaluation definitions.
  evaluationexecutebounded

How to call

https://www.evalgate.com/api/a2a

Listed in

Directories this entry was found in.