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

Agent Compatibility

No-Op Protocol

Safe stop behavior for unsupported or uncertain agents, including public review URLs and no retry-loop guidance.

  • Record UAIX-DOC-2752
  • Path /en-us/spec/no-op-protocol/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-DOC-2752
Surface
Agent Compatibility
Access
Public and linkable

How to use this page

Use this page as part of the current Agent Compatibility public record, then follow its linked standards pages for the next step.

The No-Op Protocol tells unsupported or uncertain agents to stop safely. It is a required compatibility behavior, not a failure of usefulness.

Use no-op when

  • The client cannot prove the capability level required by the action.
  • The only available path is JavaScript-only, auth-only, POST-only, MCP-only, A2A-only, or tool-only and no lower-capability fallback is listed.
  • The request would put secrets, private identifiers, regulated data, payment data, or private messages in a URL.
  • The action could publish, delete, pay, change accounts, write repositories, promote memory, or affect a regulated context without explicit review.
  • The agent would need to retry repeatedly to guess the next step.

No-op response

Code example
{ "code": "human_review_required", "url": "https://example.org/review/agent-handoff" }
Transfer formatOptimized (Keyless) JSON
Code example
[]

Field order follows the keyed JSON example, the published schema order, and the public field registry.

Required behavior

Open or cite the returned public URL, explain the missing capability or consent, and stop. Do not synthesize credentials, invent hidden URLs, retry loops, private browser steps, or writable actions.

Boundary

Agent runtimes execute. UAIX records the reviewed communication, memory, trust, evidence, and handoff boundary. UAIX.org does not execute third-party actions, certify safety, certify truth, endorse implementations, or replace local authorization policy.

Agent Compatibility Records