# Sengol

- [Sengol](https://docs.sengol.io/index.md): Signed, offline-verifiable evidence for AI agents in regulated institutions.
- [Quickstart](https://docs.sengol.io/quickstart.md): Run Sengol locally, gate an agent response, and verify the evidence offline.
- [Platform operator](https://docs.sengol.io/journeys/platform-operator.md): Install the appliance, load the licence, connect identity, and hand out access.
- [AI developer](https://docs.sengol.io/journeys/ai-developer.md): Evaluate your agent in code, record signed evidence, guard live calls, and gate releases.
- [Compliance and risk](https://docs.sengol.io/journeys/compliance-officer.md): Choose regulations, write the ControlBook, and produce reports an examiner can rely on.
- [Human reviewer](https://docs.sengol.io/journeys/reviewer.md): Work the review queue: approve or reject flagged agent decisions.
- [Auditor or examiner](https://docs.sengol.io/journeys/auditor.md): Verify an evidence pack offline, without Sengol and without trusting the vendor.
- [Audit records](https://docs.sengol.io/concepts/audit-records.md): What Sengol signs, how records are chained, and what an examiner can check.
- [ControlBook](https://docs.sengol.io/concepts/controlbook.md): Your regulations as configuration: obligations, evaluators, thresholds and scoring.
- [Guardrails](https://docs.sengol.io/guides/guardrails.md): Withhold, replace, or retry a response that fails evaluation at runtime.
- [Gate releases in CI](https://docs.sengol.io/guides/ci-gate.md): Run a golden dataset through the gate on every pull request and fail the build on a regression.
- [Access governance](https://docs.sengol.io/guides/access-governance.md): Roles, permissions, and the four-eyes controls built into Sengol.
- [Review workflows](https://docs.sengol.io/guides/review-workflows.md): Route agent intakes to the teams that must review them before approval.
- [Credentials by journey](https://docs.sengol.io/guides/credentials.md): Which credential a developer, admin, CI job or production agent uses today, what it can do, and how long it lives.
- [Evaluator library](https://docs.sengol.io/reference/evaluator-library.md): Every built-in evaluator, what it checks, and the failure mode it reports.
- [CLI](https://docs.sengol.io/reference/cli.md): The sengol command: credentials, commands by persona, and exit codes.
- [Environment variables](https://docs.sengol.io/reference/environment.md): Settings for SDK and CLI users, and for the appliance.
- [Review policy reference](https://docs.sengol.io/reference/review-policy.md): The review policy format, the facts a rule can test, and the review workflow API.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.