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

Browser and Agent Parity

Guidance for tying rendered browser evidence to static, JSON, sitemap, and llms.txt records so lower-capability clients still have safe fallbacks.

  • Record UAIX-DOC-2673
  • Path /en-us/guides/browser-and-agent-parity/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-DOC-2673
Surface
Guides
Access
Public and linkable

How to use this page

Use this guide to keep rendered browser evidence paired with static, JSON, sitemap, and llms.txt records for lower-capability clients.

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.

Browser and agent parity keeps rendered UI evidence attached to static and structured records. L2 clients can inspect a browser view, but the public record should still provide lower-level fallbacks whenever possible.

Parity checklist

  • Pair a rendered route with a static route, JSON record, sitemap entry, or llms.txt pointer.
  • State whether the browser view added information that L0/L1 clients cannot see.
  • Stop before authentication, posting, public comments, destructive actions, or memory writes unless the capability record and consent record allow it.
  • Keep screenshots or DOM notes as evidence, not as the only public truth.

When parity fails

If the only useful content is JavaScript-only, the L0/L1 records should fail or downgrade. The safe response is to name the unsupported feature and request an L2 or higher path.

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.