Inistate

Actor Parity.

The architectural principle that makes humans, AI, and hybrid actors first-class peers inside the same governed workflow.

Patent application — US Provisional #64/045,012 (filed Apr 21, 2026)

The principle.

When an AI integration uses a separate execution lane, human actions and agent actions can follow different validation, permissions, and audit paths. That makes consistent governance harder to establish.

In Inistate, there is one. The AI gets the same form, the same transition, the same audit shape as a human. The same State → Activity(Form) → State primitive. The same core fields, validation rules, and history structure, with AI metadata added for AI actions. Parity means a shared contract, not identical permissions for every actor.

We call this Actor Parity. It is the principle on which the harness rests.

Five mechanisms make Actor Parity real.

  1. 01

    Form parity.

    The AI submits the same forms a human would. Validation, required fields, transitions — identical. No "AI fast path."

  2. 02

    Transition parity.

    Every transition is State → Activity(Form) → State, regardless of actor. There is no separate state machine for AI execution.

  3. 03

    Audit parity.

    One history event shape, populated by by, on, changes, and an optional ai object containing reasoning, sources, model, model version, prompt hash, and confidence.

  4. 04

    Confidence and intention parity.

    AI-submitted transitions persist a confidence score. Below the configured threshold, the system records an intention event with flagged: true and the AI must escalate to a human for confirmation. The same primitive supports both autonomous execution and human-supervised pause.

  5. 05

    Promotion parity.

    Activities are typed: human-only, AI-only, hybrid, or any-actor. Promoting an activity from human to AI changes one field. The form, the audit, the validation — unchanged. Actor eligibility does not replace permissions or approval rules.

What it takes to unify execution.

A product with separate human and AI execution paths must reconcile its data model, transitions, permissions, and history records to deliver Actor Parity.

Reaching Actor Parity means applying the same transition contract to every actor. The implementation effort depends on how the existing product handles validation and audit recording.

Evaluate this directly: ask a vendor to run the same activity with a human and an AI, then compare the required fields, permissions, validation failures, and audit records.

"Form parity. Transition parity. Audit parity. Confidence parity. Promotion parity. Five mechanisms, one principle."

Demo 1 — Multi-Model Relay.

This example shows two model families contributing to the same workflow history.

01
Demo 1 of 7

Multi-Model Relay

User input

"go to LV 00003 and Approve it"

Audit history pane showing transitions performed by Claude Opus 4.5 and GPT-5.5 Thinking on the same Leave Application entry
Product screenshot · Select image to view at full size.

The history for Bob Wilson’s leave application LV 00003 shows Claude Opus 4.5 moving it to Submitted with confidence 95%, followed by GPT-5.5 Thinking approving it with confidence 98%. Both actions appear in the same history pane with model identity, reasoning, and confidence.

Architectural property

Actor Parity across model families. Model portability. Unified audit substrate.

What this shows

Two model families can act on the same leave workflow while retaining a shared audit format. This example demonstrates continuity across these models; each new model still needs evaluation.

→ See all seven demos

The architecture holds. Build against it.

The MCP server is the integration surface, and the published schema defines the contract. Evaluate Actor Parity by connecting a supported model and comparing its transitions and audit records with human actions. Confirm the available tools and schema version against the specification for your deployment.

Patent references

The harness architecture is described in US Patent Application Publication 20230266946 A1 (August 2023) . The Actor Parity governance extensions are described in US Provisional Application #64/045,012 (filed April 21, 2026) .