Black vs Give your AI ears

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

VoxAI is a local-first recording, transcription, and live AI copilot for macOS. It labels speakers, gives your AI the live conversation, and turns talk into advice, notes,...

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 Give your AI ears

VoxAI is a local-first recording, transcription, and live AI copilot for macOS. It labels speakers, gives your AI the live conversation, and turns talk into advice, notes, and action items. VoxAI records locally, transcribes, and labels every speaker, then gives the live conversation to the AI you already use. Get advice while you talk, then turn the full record into notes and action items. It follows the growing transcript and can push fact checks, questions, risks, strategy, and action items into the side panel.