Evaluation prototypeSchema 1.0.0

Governed Workflow State Graph

A governed, evidence-bounded record of one regulated decision — what was decided, on what evidence, under which policy, approved by whom, and whether a retry could repeat an effect.

It is not an agent memory store and not an autonomous runner. It decides and records; it never acts. Every side effect is an intent plus a receipt, and in this release the middle is simulated.

Synthetic evaluation corpus — not a customer result — evaluation-grade prototype, not a compliance certification.

The published corpus is invented for evaluation. No real claim, claimant, document, reviewer, or payment is involved. This release is not connected to payment: it makes no payments, calls no providers, and dispatches no messages.

Where it fits

Four decisions this is shaped for.

For a workflow where an organisation must later answer: what was decided, what evidence was in scope, which policy applied, who approved it, and whether a retry could repeat an effect.

Regulated approvals

Bind a reviewer’s approval to one policy version, one input, and one evidence set — so a later policy change or a revised document cannot silently inherit it.

Procurement

Require a bounded approval before an agent may prepare a purchase action, and make a lower-level exception incapable of widening what a tenant-level policy forbids.

Claims and policy review

Adjudicate against a named evidence set, with unresolved questions declared rather than absorbed into the decision.

Agentic actions

Record the intended effect, the receipt, the uncertainty, and the recovery path — so a retry after an interruption cannot quietly become a second effect.

What it guarantees

Enforced by shape, not by convention.

Each of these is enforced by the shape of the model rather than by convention, and each is covered by a test that attacks it.

Approvals bind, or they do not apply.
The approval is addressed by its content — instance, transition, policy version, input digest, evidence digest set. Change the evidence and the old approval is not found rather than silently reused.
A repeat is not a re-run.
The same idempotency key returns the original record and produces no second intent. A repeat with changed material inputs is rejected outright.
Uncertainty is declared, not absorbed.
A blocking or unresolved question routes to a human. A signed exception cannot override it.
An escalation can be resolved — only by a human.
Agents are refused. Terminal states are shut to everyone.
Documents stay outside the record.
The durable event shape has no field that can hold source text. What is retained is references, digests, bounded classifications, and caller-supplied labels.

Five steps

A bounded evaluation walkthrough

  1. 01Choose one decision. For example: approve a claim exception, approve a supplier change, or authorize an agent to prepare—not execute—an action.
  2. 02Declare the boundary. Required evidence references, policy version, approval role, allowed operation, stop conditions, and retention constraints.
  3. 03Run the workflow twice. The normal path, and one adverse path such as changed evidence, expired approval, denied policy, or an interrupted action.
  4. 04Review the evidence. Hash-chained transitions, reason codes, approval binding, uncertainty state, and recovery classification.
  5. 05Decide what would be required next. A production design needs the customer’s identity, storage, key-management, retention, integration, and control-owner decisions. This prototype does not supply them.

Discuss a bounded evaluation for a customer-shaped workflow. No source documents, provider credentials, payment authority, or live effects are needed for the initial review.

Machine-readable evidence

See it for yourself

Known limits

What this is not, yet

No external audit, no certification, and no production deployment. The reference store is in-memory. Digests are accepted from the caller, so the engine cannot detect a caller that supplies a digest for bytes it does not hold. The event chain is tamper-evident but unsigned. Connecting a real disbursement is deliberately future work, not an omission.

Synthetic evaluation corpus — not a customer result — evaluation-grade prototype, not a compliance certification. Schema version 1.0.0.