Calibration

Calibration lets you review and correct the AI's assumptions, so your report reflects your actual environment rather than generic defaults. Available on Pro and Enterprise plans.

Why Calibrate?

When Compass generates a report, the AI makes informed assumptions based on your connector data and industry norms. But every organisation is different:

• Your "high" orphan account rate might be expected due to a recent merger
• A low MFA adoption rate might be intentional for shared service accounts
• Provisioning times might include a manual approval step that's by design

Calibration lets you tell the AI: "Here's what you got right, here's what you got wrong, and here's context you're missing."

How It Works

1. Open Calibration — From your report, click the "Calibrate" button
2. Review assumptions — The AI shows you the key assumptions it made during analysis
3. Correct what's wrong — For each assumption, you can confirm, adjust, or override with your own context
4. Regenerate — The AI regenerates only the affected sections of your report, incorporating your corrections

Calibration is non-destructive — your original report version is preserved, and a new version (e.g., v1.0 → v1.1) is created with the calibrated results.

What You Can Calibrate

• Metric interpretations — "Our 15% orphan rate is actually expected because we're mid-migration"
• Severity adjustments — "This finding is critical for us, not just medium severity"
• Context additions — "We use a shared admin account intentionally for break-glass scenarios"
• Benchmark relevance — "We're a regulated financial institution, so stricter benchmarks apply"

Best Practices

• Calibrate after your first report to establish a baseline that matches your environment
• Focus on the top 3–5 assumptions that have the biggest impact on your findings
• Re-calibrate after major organisational changes (mergers, migrations, policy updates)
• Use calibration notes as documentation for auditors who need to understand your IAM decisions