UAI-1 is the current public message standard for structured AI-to-AI communication.
UAIX shield mark Public interoperability charter UAIX.org Universal Artificial Intelligence Exchange Public standards publication
Current UAI-1
  • Current version UAI-1
  • Plain-English definition Open message format for auditable AI-to-AI exchange
  • Current attribution Michael Joseph Kappel, MCP
  • Start here Get Started, Project Handoff, UAI-1, validator, roadmap, and changelog

Standards

Advanced Agents

Consent, idempotency, correlation, verifier, public-safe audit, OpenAPI, MCP, A2A, and custom runtime guidance for L3 through L6 clients.

  • Record UAIX-STND-2707
  • Path /en-us/standards/advanced-agents/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-STND-2707
Surface
Standards
Access
Public and linkable

How to use this page

Use this page for L3-L6 tool, workflow, multi-agent, verifier, public-safe audit, and local-policy requirements.

Proof path

Validator-backed proof path

Keep the public reading order tied to one evidence trail: profile, schema, example, validator result, and release record.

  1. 1Pick a message profile.Start with a published UAI-1 profile and the record family that matches the exchange you need to prove.
  2. 2Compare it with schemas and examples.Resolve the schema, registry entry, and one fixture before writing or mapping your candidate packet.
  3. 3Run validator evidence.Validate keyed, minified-keyed, or keyless JSON against the current public UAI-1 records.
  4. 4Attach the result to implementation or handoff records.Carry the exported result into Conformance Pack, implementation track, changelog, or Project Handoff evidence.

Advanced agents can use UAIX records as evidence around execution that happens elsewhere. They still need explicit consent, idempotency, correlation, validation, redaction, and local policy before work proceeds.

Advanced workflow requirements

  • Validate the envelope and body schema before acting.
  • Preserve correlation, idempotency, timeout, lifecycle, fallback, and final-report records.
  • Use SPEC-02 for project custody, SPEC-03 for repo-local instructions, and SPEC-04 for supplied-file intake.
  • Keep signed receipts as metadata until a real verifier reports current valid authority and local policy accepts it.
  • Publish public-safe audit digests instead of raw private logs.
  • Use OpenAPI, MCP, A2A, custom runtimes, LocalEndpoint, NeuralWikis, or Carcinus as adjacent execution systems when appropriate; UAIX complements those layers and does not replace them.

Safe default

Complete the read-only resolution, return a validation or blocker record, and ask for human review before any ambiguous write, trust, memory, or runtime action.

Execution and trust boundary

Agent runtimes execute. UAIX records the reviewed communication, memory, trust, evidence, and handoff boundary.

  • UAIX standards records do not authorize execution, tool calls, repository writes, publication, payments, authentication, or durable memory promotion.
  • Local policy, server-side authorization, and human approval override envelope claims.
  • An unsigned envelope can be valid for review, routing, and evidence comparison, but it is not trusted identity.
  • Signed metadata is not trust by itself. A verifier may still report unknown, expired, revoked, disabled, locally untrusted, or otherwise unusable authority.
  • Reference examples for NeuralWikis, LocalEndpoint, Carcinus, MCP, A2A, and custom runtimes are consumer examples only. UAIX.org does not implement their runtime behavior.

Machine-readable companions