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

Guides

Advanced Agent Support

Consent, idempotency, workflow, memory, coordination, audit, and evidence guidance for L3-L6 capability-adaptive agent clients.

  • Record UAIX-DOC-2672
  • Path /en-us/guides/advanced-agent-support/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-DOC-2672
Surface
Guides
Access
Public and linkable

How to use this page

Use this guide to keep L3-L6 tool, workflow, multi-agent, memory, and audited-agent support tied to consent, idempotency, correlation, fallback, and evidence.

Advanced agent support begins when a client can act, not just read. L3-L6 records require consent, idempotency, correlation, fallback, expiration, memory-review discipline, and evidence.

Level boundaries

  • L3 Tool Agent: tool calls, authentication, and posting only after explicit consent and idempotency.
  • L4 Workflow Agent: long-running external work with task status, timeout, correlation, fallback, and final report.
  • L5 Multi-Agent Runtime: external agent coordination with UAIX as the reviewed record and handoff boundary.
  • L6 Audited Agent System: provenance, audit log, validator result, consent record, memory review, and final-report evidence.

Do not widen the claim

UAIX does not run the workflow, coordinate agents, write repositories, or certify an implementation. It records the reviewed packet and validates the support claim shape.

Next records

Progressive agent access

Advanced clients should prefer POST JSON, schema validation, consent records, idempotency, correlation, fallback behavior, and evidence packets. The GET-Action Pattern remains a bounded L0/L1 fallback and is not a replacement for POST endpoints.

Agent Communication Operating Model

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

Use Agent Communication Operating Model when a human operator, coding agent, AI agent, or runtime implementer needs portable identity, intent, context, acknowledgement, status, blocker, memory proposal, validation evidence, correction, final report, or handoff records. The matching machine-readable assets are published through Schemas, Registry, Examples, and the Validator.

  • UAIX does not provide automatic sync, hosted messaging, runtime orchestration, official adapters, repository write execution, certification authority, or hosted import mechanisms.
  • Carcinus.org is a separate runtime/orchestrator example that may consume UAIX records. UAIX.org does not implement Carcinus runtime behavior and does not execute Carcinus workflows.
  • LocalEndPoint and other runtimes may consume the published UAIX records as external consumers; UAIX.org does not implement their project-specific runtime features.
  • Durable memory proposals stay separate from task execution records. Do not promote temporary endpoint statuses, session tokens, write tokens, beta platform instructions, local error traces, private keys, or API credentials.