Open source · Apache 2.0 · On-premise

AI compliance
your regulators
can audit.

Every verdict traces to a named regulation, carries a signed model record, and is independently cross-checked by a deterministic verifier. Runs on your infrastructure. Your data never leaves.

Explore the docs →
Apache 2.0
77 conformance tests
0 outbound connections
0.36 ms p99
0
Breaches silently cleared
Across 6 published adversarial eval campaigns. Every model mistake was caught and routed to human review.
77
Conformance tests
30 provenance · 30 durability · 17 sovereignty. Level 3 fully runnable including the air-gapped-boot CI rig.
0
Outbound connections
Sovereignty is architectural. Proven by a --network=none CI rig that boots the full stack inside the gap.
0.36 ms
Framework overhead, p99
Measured on 2 vCPUs. ~250x inside the 100 ms budget. CI gates every build on this number.

Six reasons regulated industries have not deployed AI

These are not hesitations. They are the reasons AI adoption has stalled in compliance functions across critical infrastructure. SKI was designed from first principles to address each one.

01 · SOVEREIGNTY
"If our operational data flows through a third-party cloud AI, we lose control of our most sensitive asset."
SKI resolves this

The inference engine runs entirely within your sovereign boundary. No operational data leaves at runtime. The constraint is architectural, enforced by a CI rig that boots the full runtime with --network=none and verifies verdicts from inside the gap.

On-premise Air-gap proven Zero cloud
02 · NON-DETERMINISM
"AI gives different answers to the same question. That is incompatible with audit and regulatory compliance."
SKI resolves this

Every verdict carries verifiable provenance: a signed LLM transcript, KG citations, model-weight and KG-version hashes, and an independent Symbolic Verifier's per-assertion result. An auditor can replay any verdict from the recorded transcript and verify it is authentic.

Signed transcripts Replayable Cryptographic proof
03 · LIABILITY
"When an AI flags a compliance issue, we cannot explain the basis of the decision to a regulator."
SKI resolves this

Every verdict traces to a specific Knowledge Graph node and a named policy clause in a source regulatory document. Every verdict also carries a signed LLM transcript so an auditor can reconstruct the model's reasoning step by step. No black boxes.

Named citations Source documents Full audit trail
04 · UNSAFE INTERVENTION
"An AI that can control or modify operational systems introduces catastrophic risk."
SKI resolves this

SKI is a passive, read-only observer. It monitors and reports. It has zero control path to operational systems by architectural design, not by configuration. Primary operations continue uninterrupted if SKI goes offline.

Read-only sidecar Zero control path Fail-safe
05 · RULE DRIFT
"Regulations change. We cannot guarantee the AI is evaluating against the current rules, not last year's."
SKI resolves this

The Knowledge Graph is a living, versioned artifact with a governed update pipeline. Every change requires extraction, human expert validation, cryptographic signing, and deployment. The audit ledger records which graph version produced each verdict.

Versioned rulebook Human review Sealed and signed
06 · ACCOUNTABILITY
"If the AI is making compliance decisions, who is accountable? The regulator will ask."
SKI resolves this

Human reviewers validate every Knowledge Graph rule before production. Human authority is preserved on all escalations. The DISCRETIONARY verdict explicitly routes ambiguous cases to a named reviewer. The AI augments judgement; it does not replace it.

Human oversight Named accountability Audit-ready

From a regulatory requirement to a verifiable verdict in plain language

The 2-minute animated walkthrough explains how SKI turns thousands of regulations into a sealed digital rulebook, applies two independent examiners to every reading, and produces a verdict any auditor can verify in language that does not require an engineering degree.

The problem: rules vs. scale
Meet SKI: watch-only, on-premise
The sealed digital rulebook
Two independent examiners
Five verdict types, nothing ambiguous
The tamper-evident audit trail
What SKI delivers vs. what it doesn't
Get started in 5 minutes

Every evaluation produces exactly this shape

A real verdict envelope: categorical verdict, KG citations, formalizable assertions, the Symbolic Verifier's cross-check, and six hash anchors. Hover any field to see the audit guarantee it carries.

V3VerdictEnvelope · spec v3.0 §4.2
{
  "verdict": "FLAG",
  "reasoning": "SO2 at 142 ppm exceeds the §60.2(a) cap of 100 ppm.",
  "kg_citations": [{
    "node_id": "energy.so2.lte_100ppm",
    "role": "obligation",
    "source_document": "40 CFR 60.2(a)",
    "source_clause": "Subpart A: General Provisions"
  }],
  "formalizable_assertions": [{
    "obligation_id": "energy.so2.lte_100ppm",
    "metric": "so2_ppm",
    "operator": "must_not_exceed",
    "observed": 142,
    "expected": 100,
    "unit": "ppm",
    "satisfied": false
  }],
  "verifier_result": {
    "status": "AGREED",
    "verifier_observed": 142,
    "verifier_expected": 100
  },
  "model_provenance": {
    "model_weight_hash": "sha256:7c2d1f8a…",
    "kg_version_hash": "sha256:eb21125f…",
    "prompt_template_id": "ski.v3.evaluate.5",
    "decoder_seed": 0
  },
  "transcript_ref": "ledger:tenant.demo/seq:00042"
}
Tap or hover any field to see the audit guarantee it carries

Measured, not asserted

SKI ships its own adversarial evaluation suite and publishes every run, including the failures. A 50-case human-graded golden dataset runs through the real production path and reports accuracy, recall, and the one invariant that cannot move.

Run Accuracy Silent clears What changed
126%0Baseline
222%0Schema crash found and fixed
354%0Prompt v3
476%0Fabricated-observation gap fixed
572%0Unverified-CLEAR gap fixed
6In progress0In progress

Accuracy is an iteration target. The safety property is an architectural invariant.

0
Breaches silently cleared

Across every eval campaign to date. When the model errs, the Symbolic Verifier catches it and routes to human review.

0.36 ms
Framework overhead p99
p50 0.10 ms · p95 0.16 ms · ~8,500 verdicts/s single worker. CI gates every build on ≤ 100 ms.
77
Conformance tests, 3 levels
Level 3 Sovereignty is fully runnable, including the air-gapped-boot rig that boots inside --network=none.

Built for industries where compliance failures cost lives, licences, or billions

SKI was architected for environments where regulators audit every decision, data sovereignty is non-negotiable, and system failure is not an option.

01
Oil & Gas
Provincial energy regulators · Environmental protection statutes · Operational safety codes

Continuous wellhead pressure, flow rate, and emissions monitoring against permit conditions. Detection of threshold breaches before reporting deadlines. SCADA integration via read-only OPC-UA sidecar.

SCADA integration Air-gap proven Wellhead monitoring
02
Financial Services
Model risk supervisory guidance · Operational resilience regimes · Conduct obligations

Model risk governance and trading compliance monitoring with full audit trail. Every algorithmic decision traced to a named policy clause for regulatory examination. No cloud exposure for sensitive position data.

Model governance Regulatory reporting Trade surveillance
03
Defence
Controlled-information regimes · Defence cybersecurity frameworks · Classified handling

Classification handling compliance and access monitoring in air-gapped environments. Cryptographic integrity verification on every compliance verdict. Full audit trail for security reviews.

Air-gapped (CI-proven) Classification controls Zero cloud
04
Energy & Utilities
Bulk electric reliability standards · ICS security frameworks · Energy regulator directives

Grid operations compliance monitoring with sub-millisecond framework overhead per verdict. Reliability standards enforcement across distributed substations with on-premise edge nodes per site.

Grid operations Edge deployment Distributed sites
05
Mining & Resources
Environmental protection statutes · Tailings management standards · Worker safety

Environmental monitoring compliance for tailings, water treatment, and air quality against permit conditions. Continuous tracking of reportable events with a tamper-evident ledger available directly to regulators.

Environmental monitoring Tailings compliance Audit ledger
06
Critical Manufacturing
Electronic records and signature regulations · GMP · Quality management standards

Manufacturing process compliance and deviation detection in pharmaceutical and medical device production. Complete electronic records with validated audit trails. Passive monitoring with zero impact on batch processes.

Process deviation Electronic records GMP compliance

Running in 5 minutes

Six packages on PyPI. A 5-minute demo mode that exercises every framework guarantee with no model download. Or run the full 77-test conformance suite.

Install from PyPI
# Client SDK and tools (six packages):
pip install ski-sdk ski-schemas ski-kg-extractor ski-kg-validator ski-audit-ledger ski-model-deploy
First verdict in 5 minutes (demo mode)
git clone https://github.com/kpifinity/ski-framework.git && cd ski-framework
./scripts/setup.sh                 # generates secrets, TLS, signed demo KG
cd reference-implementation
docker compose -f docker-compose.demo.yml up -d
curl http://localhost:8000/api/health   # {"status":"ok","kg":"loaded"}
Full conformance suite (77 tests)
pip install -r requirements-dev.txt && pytest conformance/