AI that can prove it's right

Encode any rule, policy, or law as code that returns the same answer every time, with a proof of why. Language models synthesise the rules at build time. A constraint solver evaluates them at decision time.

Affordability check for unsecured consumer credit.

curl -X POST https://api.aethis.ai/api/v1/public/decide \
  -H "Content-Type: application/json" \
  -d '{
    "ruleset_id": "aethis/consumer-credit-prequalification",
    "field_values": {
      "credit.has_adverse_history": false,
      "credit.employment_status": "employed",
      "credit.gross_annual_income": 50000,
      "credit.has_joint_applicant": false,
      "credit.joint_annual_income": 0,
      "credit.dti_percent": 25,
      "credit.credit_score_band": "excellent",
      "credit.product_type": "unsecured",
      "credit.ltv_percent": 0,
      "credit.stress_test_passed": true,
      "credit.is_existing_customer": true
    },
    "include_trace": true
  }'
Try it in your terminal
curl -X POST https://api.aethis.ai/api/v1/public/decide \
  -H "Content-Type: application/json" \
  -d '{
    "ruleset_id": "aethis/uk-fsm/child-eligibility",
    "field_values": {
      "child.age": 10,
      "child.school_type": "state_funded"
    }
  }'
Returns the decision, a per-criterion trace, and the audit envelope.
No signup, no key. Public ruleset, anonymous endpoint.
Or use the Python SDK, CLI, or MCP →Using Claude Code, Cursor, or Windsurf?Agent onboarding →

Navigation, not just decisions.

Legislation isn't a checklist. It's a forest of criteria with branches, exceptions, and alternative routes. Aethis maps the traversable paths through the rules and guides a user towards the best outcome given their situation — surfacing viable routes, not just a verdict.

Soft constraints find the path. Hard constraints hold the law.

What is Aethis?

Aethis compiles legislation, policy, and contracts into formally verified rules. Language models read the source at build time and synthesise candidate rules; subject matter experts (SMEs) write tests that define correct behaviour; the engine refines rules until every test passes. At decision time, a constraint solver evaluates the compiled rules against the supplied facts. No language model in the request path. Every decision returns a proof and an audit trail traceable to the source.

0
LLM calls in the request path
100%
accuracy where frontier LLMs score 63-100% Simpson 2026 §3
1,000×
faster than a frontier-LLM call
£0
marginal cost vs ~$0.02 per LLM call

How does Aethis compare?

How Aethis compares to other ways of making rule-based decisions.

CapabilityAethisLLM onlyStatic rules engineDecision tree
Same input → same outputYesNoYesYes
Source-cited audit trailYesNoManualPartial
Authoring from source textLLM-assistedn/aManualManual
Handles legislation directlyYesYes (probabilistic)Hand-encodedHand-encoded
Auditable for regulated workflowsWhen rules are explicit and validatedNot deterministicYes (no source traceability)Yes (fixed branching)
supported not supported
Full comparison in the docs →

Ready to build?

Early access is open. Tell us what you're building.

Request developer access