Black vs Skillburst

A black-box evaluation of how AI-generated tests find functional bugs in live APIs.

Turn your team’s best AI workflows into approved skills, help teammates use them in supported AI assistants, and measure real adoption.

About Black

A black-box evaluation of how AI-generated tests find functional bugs in live APIs. The harder question is whether those tests find bugs. Each system receives only a JSON schema and one valid sample payload, then must generate API test cases that expose failures in a live reference API. The evaluation uses APIEval-20 v1.0, a black-box benchmark contributed by KushoAI. Because KushoAI is also one of the evaluated systems, this report includes the methodology, workflow definitions, repeated-run setup, and robustness checks so readers can understand where the performance difference comes from.

About Skillburst

Turn your team’s best AI workflows into approved skills, help teammates use them in supported AI assistants, and measure real adoption. Turn your team's best AI workflows into approved skills people can use inside the assistants they already have. For AI & platform leads Turn expert workflows into a repeatable rollout. Invite the right pilot group, see where setup stalls, and measure real use. For teammates Use the workflow without learning prompt engineering. Connect a compatible assistant and ask for the approved skill by name.