
Verify agent outcomes, not just tool calls.
AI agents often report success because a tool call completed, even when the actual outcome is wrong or incomplete. DidWork independently verifies agent work against the expected result, gives agents clear pass/fail gates, and can trigger repair when verification fails. It works through MCP and an SDK, supports multiple providers, and produces shareable verification receipts so developers can see what was checked and whether the work was actually done.
DidWork verifies the outcomes of AI agents by comparing their results against expected outcomes, providing pass/fail assessments and triggering repairs when necessary. It integrates with multiple providers through MCP and an SDK, generating shareable verification receipts for developers.
A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.