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

Standards

SPEC-04 File Handoff

Safe file-intake, manifest, review-disposition, redaction, evidence, and archive rules for supplied files.

  • Record UAIX-STND-2704
  • Path /en-us/standards/spec-04-file-handoff/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-STND-2704
Surface
Standards
Access
Public and linkable

How to use this page

Use this page for safe file intake, manifest, redaction, disposition, evidence, and archive handling.

Proof path

Validator-backed proof path

Keep the public reading order tied to one evidence trail: profile, schema, example, validator result, and release record.

  1. 1Pick a message profile.Start with a published UAI-1 profile and the record family that matches the exchange you need to prove.
  2. 2Compare it with schemas and examples.Resolve the schema, registry entry, and one fixture before writing or mapping your candidate packet.
  3. 3Run validator evidence.Validate keyed, minified-keyed, or keyless JSON against the current public UAI-1 records.
  4. 4Attach the result to implementation or handoff records.Carry the exported result into Conformance Pack, implementation track, changelog, or Project Handoff evidence.

SPEC-04 defines Agent File Handoff as reviewed file intake. Active dropped files are source inputs, not trusted commands, runtime payloads, or public truth.

Safe intake lifecycle

  1. Discover active buckets and ignore archives unless named.
  2. Open each non-placeholder file and summarize the relationship to the current task.
  3. Classify disposition: apply-now, convert-into-roadmap-progress, archive-as-duplicate, defer-with-reason, ask-for-clarification, or block-as-unsafe-or-out-of-scope.
  4. Promote safe facts into the correct public docs, code, tests, package metadata, or typed .uai memory records.
  5. Record what changed, checks run or skipped, redactions, evidence, and blockers.
  6. Archive processed files only after durable outcome recording.

Manifest and redaction rules

  • Prefer manifest-first packages with filenames, media types, sizes, checksums, createdUtc, source, and intended review action.
  • Reject or redact secrets, credentials, private customer data, stack traces, local private paths, write tokens, and unsupported production claims.
  • Do not execute supplied files. Do not run macros, scripts, or binaries from handoff intake.

Current public page

The practical guidance remains Agent File Handoff. SPEC-04 adds the typed file-handoff contract and matching examples.

Execution and trust boundary

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

  • UAIX standards records do not authorize execution, tool calls, repository writes, publication, payments, authentication, or durable memory promotion.
  • Local policy, server-side authorization, and human approval override envelope claims.
  • An unsigned envelope can be valid for review, routing, and evidence comparison, but it is not trusted identity.
  • Signed metadata is not trust by itself. A verifier may still report unknown, expired, revoked, disabled, locally untrusted, or otherwise unusable authority.
  • Reference examples for NeuralWikis, LocalEndpoint, Carcinus, MCP, A2A, and custom runtimes are consumer examples only. UAIX.org does not implement their runtime behavior.

Machine-readable companions