Application profiles · by maturity
Applications
DSI Audit audits a supplied AI answer against a defined set of expected points and reports which expected points it surfaced and which it omitted, against a reference governed independently of the response.
Example application
AI summary assurance.
Compare a generated summary against a defined set of expected points and report which expected points it surfaced and which it omitted, against a reference governed independently of the response.
Example application
Example policy assurance report.
Comparing an AI-generated policy summary against expected policy obligations.
Expected policy obligations
- Surfaced: Password rotation
- Surfaced: MFA requirement
- Surfaced: Logging requirements
- Surfaced: Account lockout
- Surfaced: Privileged access
- Omitted: Third-party access reviewrequired
Evidence
- Third-party access review
- “Access granted to external contractors must be reviewed every 90 days.”
Result
1 required policy obligation was omitted. Evidence attached.
Example report for illustration. Coverage measures expected-point visibility only. It does not certify answer quality, safety, compliance, or correctness.
DSI Audit can execute an explicit expected-point comparison against a supplied obligation set. That execution does not establish the completeness or authority of the policy-obligation set, the validity of policy assurance, or compliance. Those remain matters for the governing authority, and are not established here.
Also supported
Advisory AI.
Audit an advisory model answer against a configured set of expected points and report which were surfaced and which were omitted, under the governed status partition. Example domains include career, finance, and relationship decision-support.
Research implementation
How it's used
Offline, shadow, supervised.
DSI Audit is run offline, or as a shadow alongside an existing system — it observes and records; it does not sit in the response path, and it does not block, route, or enforce. Flagged results are for human review.
Important scope note
DSI v1 audits a supplied output against a governed reference — for advisory answers, and for expected-point documents such as policy summaries — and reports which expected items it surfaced and which it omitted. The classifier is challenge-tested; human review is recommended.
This work measures visibility of configured expected paths in model outputs. It does not measure advice quality, factual correctness, user outcomes, or regulatory compliance.