Overview
ProofRun helps developers answer a critical question before shipping: will this update break behavior users rely on?
An AI agent inspects two Git revisions, designs targeted experiments, and proposes repairs. An independent Docker-based verifier runs those experiments against both versions, preserves the original tests, and checks whether the repair actually works. Developers receive an update, skip, or postpone recommendation with recorded evidence and a reviewable patch.
In a live synthetic evaluation, ProofRun discovered two customer-ID regressions and independently verified a repair in under four minutes, without being given a failing request or prepared fix.
ProofRun integrates with DuploCloud for its workflow and evidence interface, OpenRouter for AI investigation and repair, Crusoe serverless inference for an additional repair provider, and Neo4j for deployment relationships and verification history. Verification runs locally in isolated Docker environments.
Note: the demo URL is substituted with the GitHub repository link.
