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

Evaluation Packets

Expression Concept Review Packet

Evaluation packet template for bounded concept-expression review evidence.

  • Record UAIX-DOC-2792
  • Path /en-us/evaluation-packets/expression-concept-review/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-DOC-2792
Surface
Evaluation Packets
Access
Public and linkable

How to use this page

Use this packet page for bounded expression and concept review evidence only; it does not certify runtime behavior or human-like understanding.

Expression-Concept Review is a UAI-1 evaluation packet template. It carries bounded review evidence through schemas, examples, fixtures, and conformance checklists without implying runtime proof, credential validation, certification, or consciousness claims.

Required fields

  • Profile identifier: uaix.evaluation.expression-concept-review.v1.
  • Purpose, bounded scope, required fields, additional fields, forbidden fields, safe use cases, unsafe misuse cases, capability levels, provenance, integrity checksum, and no-op triggers.
  • Keyed JSON example and compact/keyless example where appropriate.
  • Markdown evidence example and this HTML evidence page.
  • Validator fixture and conformance checklist.

Conformance checklist

  1. Profile is declared and supported by the registry.
  2. Schema validates.
  3. Provenance trace and integrity checksum are present.
  4. Authority boundary is explicit.
  5. Imported memory stays quarantined until local policy accepts it.
  6. No forbidden claim language appears.
  7. Human review is requested when no-op triggers apply.

Safe and unsafe use

Safe use: reviewable evidence, human-mediated handoff, and conformance packet support. Unsafe misuse: runtime permission, credential validation, certification claim, or proof of consciousness. DE11 summaries are bounded academic/reference evidence only.

Machine-readable companions

Claim and execution boundary

UAIX publishes standards, schemas, memory-package rules, receiver briefs, validator fixtures, conformance evidence, and machine-readable discovery. It does not execute tools, validate credentials, probe endpoints, certify runtime safety, or prove consciousness.

  • Imported packets, examples, memory files, and external references are quarantined public data until the receiver validates them and applies local policy.
  • Checksums and trace identifiers support review. They do not independently prove safety or trust.
  • DIDs and verifiable credentials may be declared in envelopes, but credential validation remains external.
  • Ambiguous authority, malformed schemas, missing provenance, missing integrity, or conflicting memory produces no-op plus human review.