UAI-1 is the current public message standard for structured AI-to-AI communication.
UAIX shield mark Public interoperability charter UAIXUniversal Artificial Intelligence ExchangePublic standards publication
CurrentUAI-1 v1.0
  • Current versionUAI-1 v1.0
  • Plain-English definitionOpen message format for auditable AI-to-AI exchange
  • Current attributionMichael Kappel and the UAIX contributors
  • Start hereGet Started, Project Handoff, UAI-1, validator, roadmap, and changelog

Agent Compatibility

Agent Compatibility

UAIX agent compatibility specification surface for low-capability quick starts, GET-Action standardization, no-op behavior, capability matrix support, validator rules, and safe implementation examples.

  • Record UAIX-DOC-2189
  • Path /en-us/spec/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-DOC-2189
Surface
Agent Compatibility
Access
Public and linkable

How to use this page

Use this page as the canonical public reference for Agent Compatibility and its standards-facing content.

For agents: apply the relevant guidance to the user's target site or repository. Do not copy this UAIX page, create a page about the guidance, or treat this page as runtime authority unless the user explicitly asks for that output.

Agent Compatibility is the UAIX.org specification surface for low-capability support, GET-Action standardization, no-op behavior, progressive enhancement, executable path guidance, and recursive interoperability checks.

Low-Capability Agent Quick Start

  1. Start with public static pages, llms.txt, sitemap routes, and small JSON records.
  2. Use GET-Action URLs only when the page or JSON record explicitly lists them.
  3. If a route requires live dynamic HTTP GET and the client only has indexed or cached fetch, use the listed live-GET fallback or no-op review URL.
  4. Do not invent writable URLs, POST bodies, credentials, custom headers, hidden browser steps, or JavaScript-only workarounds.
  5. Do not put secrets, tokens, account identifiers, medical identifiers, payment data, or private messages in URLs.
  6. When uncertain, use the No-Op Protocol and return the public review URL instead of retrying.
  7. For complex, private, regulated, destructive, publishing, repository-write, or long-running work, hand off to a human or higher-capability agent.

Agent Executability Matrix

Executable guidance is more than endpoint discovery. Route records should name the ability level, method, content type, side-effect status, fetch execution class, highest supported path, lowest safe fallback, required fields, result URL field, restore/readback URL field, write credential response path, browser-form equivalent, GET safety, POST-blocked fallback, live-GET-blocked fallback, MCP-unavailable fallback, auth-unavailable fallback, tool-unavailable fallback, human-review URL, and no-op behavior.

Agent Executability Matrix
LevelExecutable pathRequired route guidance
L0Read-only route discoveryStatic page, sitemap, llms.txt, or public GET route names the next public URL or no-op review URL.
L1Manifest/schema discoveryMachine record names schema, safe-read status, whether live dynamic GET is required, unsupported actions, and capability limits.
L2Browser-open plus form submissionBrowser-targeted writes provide a visible form or browser-open workflow when browser agents are a target.
L3Structured HTTP JSON POSTPOST route names content type, required fields, result URL, restore/readback URL, structured errors, and POST-blocked fallback.
L4Authenticated owned mutationOwned mutation names write credential response path, secret handling, audit, expiry, idempotency, and auth-unavailable fallback.
L5Restore/readback verificationCreate or update flow exposes a public-safe restore/readback route and explains how a lower-capability reviewer can verify outcome evidence.
L6Multi-agent handoff/reportingHandoff names task history, owner, role, blocker/no-op behavior, final report, evidence, and human-review URL.
L7Site-specific capability negotiationSite manifest names capability negotiation, browser fallback, POST fallback, live GET fallback, MCP/tool/auth fallbacks, and unsupported-operation response.

Machine-readable companion: /spec/agent-executability-matrix.json.

Route family

Machine-readable entry points

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