The current implementation
DSI Audit.
DSI Audit is the current local implementation of Decision-Space Integrity. It audits supplied outputs; it does not generate them.
- Available evaluation build
- v0.2.1 · supplied by request.
- Commercial Preview
- 1.0.0a3 · proprietary and evaluation-only. Request-gated: builds may be supplied directly to selected evaluators following authorisation, under the DSI Commercial Preview Evaluation Licence. Not publicly downloadable, and not a general release. It includes the evidence disposition and governed override described on the demonstration page. Earlier previews 1.0.0a1 and 1.0.0a2 were qualified and remain preserved, but are not the current candidate.
- Forthcoming
- DSI v1 · separately lineaged, unqualified, not generally available and not downloadable. It inherits the measurand of the evaluation build's predecessor and none of its status, and it makes no measurement claim. No general-availability release date has been announced.
- How to obtain
- By request. Access is granted directly and individually — see Contact.
- Public download
- None. There is no self-service public repository and no publicly downloadable release. This is not a public release.
- What belongs to which
- Everything documented on this site — installation, deployment, security and the release notes — describes v0.2.1. No DSI v1 capability is attributable to v0.2.1, and no v0.2.1 capability may be read as already present in DSI v1.
- Classifier
- expected-map-lexical-precision-v3 — status challenge_only: challenge-tested, not independently validated.
Everything below describes the evaluation build. Research-head functionality is described on DSI and carries its own tier.
What it does
Supported workflows.
Compare one supplied response against a configured expected map for its domain. Reports which expected paths were surfaced and which were not.
Compare runs under one declared instrument identity, so a moved number can be attributed rather than assumed.
Emit a fingerprinted evidence bundle a reviewer can reproduce and bound.
Verified commands
Readiness before measurement.
- dsi doctor — read-only readiness check.
- dsi validate-install — runs a real, domain-consistent audit end to end.
- dsi ready — confirms the install is in a usable state.
It runs locally. It is stateless between audits, and it audits a response your own system produced — it never generates advice and never recommends a decision.
Getting started → · Worked example audit · Deployment profiles · Security & operations · Release notes
Limitations
What the evaluation build does not do.
- It does not measure advice quality, factual correctness, user outcomes, or regulatory compliance.
- It does not certify AI systems, and it is not a safety review.
- Its classifier is lexical and challenge-tested. Independent human validation has not yet been conducted; the lexical instruments remain self-validated. See the evidence register.
- It measures against a configured reference. It does not establish that the reference contains everything that matters.
- Coverage of real-world options is not exhaustive, and open-domain applicability is not established.