Reference integrations

Plug Signatrust into a real evidence pipeline in one afternoon.

These reference integrations show the smallest useful architecture for independently verifiable AI decisions: assessment, authorization, execution, receipt issuance, and third-party verification. They are designed for technical due diligence, research environments, and regulated pilots.

Evidence pipeline

What these integrations prove

The goal is not to impress with UI. The goal is to prove that a partner can generate a Decision Receipt inside its own workflow, then verify it later without trusting the original system.

1
Assess risk and context

Capture the policy route, risk level, model choice and execution conditions before a consequential action happens.

2
Authorize the action

Record whether a human or a system policy authorized execution, and seal that information into the same evidence trail.

3
Seal the decision

Hash content locally, issue an Ed25519-signed Decision Receipt, and append it to the existing Signatrust hash chain.

4
Verify independently

Use only the receipt and public verification endpoints to prove integrity, signature validity and ledger linkage.

Available examples

One repository, multiple integration surfaces

JavaScript

Minimal Node.js reference flow that registers an agent, seals a healthcare decision, and verifies the receipt immediately.

Python

Standard-library example for teams that want zero third-party dependencies in the base proof-of-concept.

REST API

Raw HTTP flow for buyers that want protocol-level evaluation before touching an SDK.

FastAPI

A lightweight authorization service showing Signatrust as the evidence layer inside an application endpoint.

LangGraph

Graph-based orchestration example with step-level sealing under one shared trace id.

n8n

Workflow-native example for operational teams that want low-friction sealing inside automation flows.

AI system | v Risk assessment / policy context | v Authorization | v Execution | v Signatrust Decision Receipt | v Independent verification

For research and assurance teams

Why this format is stronger than a dashboard demo

Research-ready evaluation path

  • Run the integration against a local or hosted Signatrust node.
  • Generate a receipt for a real or simulated consequential AI action.
  • Verify the receipt later from a separate process or environment.
  • Inspect how authorization and policy context are preserved as evidence.

What to ask first

  • Can a third party verify the receipt without privileged backend access?
  • Can the integration fit inside an evidence pipeline rather than beside it?
  • Can the same trust model work across healthcare, public sector and regulated enterprise use cases?
  • Can step-level sealing expose chain of custody for agentic workflows?
Current note: the FastAPI and LangGraph examples are documented for Python 3.11–3.13 because the current Pydantic ecosystem is not yet reliable on Python 3.14 beta runtimes.

Need a partner-specific evaluation package?

Start with the reference integrations repository, then adapt the same evidence pipeline to your domain: healthcare, public-sector decisions, finance, or operational agents.