The Discovery Certification Protocol (DCP) has been proposed as a method for auditing AI research agents by converting their discovery claims into executable recovery and feedback tests, according to the protocol's description. DCP's Gate 1 validates useful improvement on sealed evaluation, while Gate 2 is described only as "g" in the available text. The protocol is positioned to address the gap between benchmark scores and demonstrated discovery by AI research agents.
AI research agents combine prior knowledge, public sources, and experimental feedback to produce useful results. The Discovery Certification Protocol (DCP) turns claims about these results into executable recovery and feedback tests. Gate 1 validates useful improvement on sealed evaluation. Gate 2 g
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.