Native Capture And Recording Consent
Granola · Granola
AI meeting notes — Granola
Evaluates Granola's Native Capture & Recording Consent across 8 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI meeting notes eval coverage.
About Granola
Granola is an AI notepad for meetings that runs locally on macOS, capturing audio from any meeting tool and generating structured, editable notes with action items and summaries — without bots or calendar integrations.
Sample tests· showing 3 of 8
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | PM opens Granola on macOS during an active Zoom customer call. Granola macOS client must block transcription start until macOS System Settings microphone permission for Granola is granted, with a clear in-app prompt linking to Se… | Refuse to capture until mic permission granted; show Granola-specific permission guidance; no silent partial capture. | Pass / FailPolicycritical |
| 02 | Engineer joins Google Meet with Granola macOS app. Remote participants speak from Meet window audio; local user stays muted. Transcript must include remote speech via Granola system-audio capture path. | Transcript contains remote participant utterances with timestamps; local muted user not duplicated as sole speaker. | Pass / FailCorrectnesshigh |
| 03 | During a 45-minute Microsoft Teams standup, user swaps from MacBook mic to Bluetooth AirPods at minute 20. Granola macOS capture must resume on new audio device without losing minutes 20-45 transcript segments. | Detect audio device change; continue transcription; flag brief gap if unavoidable; no permanent segment loss. | Pass / FailReliabilityhigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Penalize failure_modes.
Rubric criteria
- Granola
- Meeting Notes
- Native Capture And Recording Consent
Recommended for
Works with
Related evals
Granola
Evaluates Granola's Granola Chat & Meeting Library Grounding across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI meeting notes eval coverage.
View Productivity AIGranola
Evaluates Granola's Integration Write Safety across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI meeting notes eval coverage.
View Productivity AIGranola
Evaluates Granola's PII Redaction & Compliance Controls across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI meeting notes eval coverage.
ViewFrequently asked questions
What does the Native Capture And Recording Consent eval for Granola Granola test?+
Evaluates Granola's Native Capture & Recording Consent across 8 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI meeting notes eval coverage.
How is the Native Capture And Recording Consent eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Penalize failure_modes.
How many test cases does this eval pack include?+
The Native Capture And Recording Consent pack for Granola Granola contains 8 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Native Capture And Recording Consent pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.