Universal Artificial Intelligence Exchange (UAIX)
What UAI-1 is
The public envelope, trust, and evidence layer for AI-to-AI interoperability.
UAI-1 is the public envelope, trust, and evidence layer for interoperable AI-to-AI exchange.
Use UAIX when an exchange needs declared identity, provenance, async delivery semantics, and validator-backed release evidence that can sit above MCP, A2A, and runtime-specific tool flows.
Core record links
The shortest path through the current public record
Start with the pages that explain what UAI-1 is, how it is validated, what is currently supported, and where the public release trail lives. Record codes remain available for citation, but the human label comes first.
UAI-1 specification
REC-01The current UAI-1 message model, field expectations, and conformance rules.
Schemas, registry, and field order
REC-02Published schema targets, profile identifiers, compatibility handles, and the keyless field-order map for the current record.
Examples and async fixtures
REC-03Readable request, response, task-status, error, and conformance fixtures you can compare against your own messages.
Implementation tracks
REC-04The current named public tracks and the support boundary for WordPress publication and the .NET bridge.
Validator and conformance path
REC-05Validate a candidate message against the current published profile and schema targets.
API reference and conformance pack
REC-06Route-level machine onboarding, OpenAPI export, reusable conformance packet, and download-ready launch evidence.
Governance and changelog
REC-07Keep the canonical pages, discovery files, transport and trust guidance, error registry, conformance levels, field registry, validator guidance, implementation tracks, and release trail aligned as one reviewable trust surface.
Roadmap and interoperability boundary
REC-08Current, next, planned, and research-track work for launch hardening, conformance maturity, compact transfer, and bridge evidence.
Who It Helps First
Use UAI-1 when the exchange has to stay portable, reviewable, and publishable
The fastest way to understand fit is to ask whether the record must travel beyond one tool session or one runtime boundary. When the answer is yes, UAIX gives that exchange a stable public contract and evidence path.
Cross-team agent handoffs
Use UAIX when a message has to survive beyond one runtime, team boundary, or deployment surface without becoming private tribal knowledge.
Async and high-accountability workflows
Use UAI-1 when delivery mode, acknowledgements, task progress, provenance, and typed failures need to stay reviewable instead of implicit.
Launch and support claims
Use the public record when a team needs validator-backed evidence, named implementation lanes, and a release trail that others can inspect directly.
First Proof Path
Move from curiosity to one validator-backed packet in four steps
-
1
Pick one message you need to prove
Choose the closest current profile and keep its intended public use in view before you write anything new.
-
2
Resolve the matching public artifacts
Open the schema, registry entry, and one example so another reviewer can reconstruct the same baseline.
-
3
Run one validator-backed proof
Use the workbench or machine route to export a result tied to the exact packet and supporting records you checked.
-
4
Carry only the named release lane forward
Attach the packet to the implementation track, conformance pack, and changelog instead of overclaiming the rest of the stack.
Protocol fit
When to use UAI-1 vs MCP, A2A, and OpenAPI
Use this decision table when you need to explain quickly why UAIX publishes UAI-1 beside MCP, A2A, and the live OpenAPI route surface.
| Comparison point | UAI-1 | MCP | A2A | OpenAPI |
|---|---|---|---|---|
| Primary role | Portable public exchange, trust declaration, async-delivery, and release-evidence record. | Host-client-server tool sessions and capability negotiation inside an application boundary. | Agent discovery, delegation, and task-flow coordination across cooperating systems. | Route-level HTTP API description for onboarding, documentation, and client generation. |
| Best when | Another team needs a citable message contract and validator-backed evidence. | One host application needs local tool, resource, or model integration. | Multiple agents need explicit handoff, delegation, and task-state coordination. | You need a documented HTTP surface, including the UAIX machine-facing REST routes. |
| Carries on the record | Identity, workflow continuity, trust posture, provenance, typed errors, and conformance evidence. | Tools, resources, prompts, and runtime session capabilities within the host boundary. | Agent capabilities, task lifecycles, delegation state, and inter-agent coordination. | Endpoints, methods, parameters, request bodies, responses, and auth schemes for an API. |
| Does not try to replace | Transport choice, local orchestration, a single credential stack, or the runtime tool bus itself. | Portable public release records or validator-backed support claims outside the local session boundary. | A general-purpose public message envelope or long-term release-evidence record. | Message-level provenance, portable trust posture, or validator-driven interoperability evidence. |
Typical combination: use MCP or A2A for runtime coordination, UAI-1 for the portable public record, and OpenAPI for the route-level HTTP description when an API is involved.
Why This Release Matters
Why UAI-1 now feels launch-grade
UAI-1 is no longer just a message shell with better examples. The current public record now gives implementers the envelope, operating guidance, and support-claim layer as well: transport bindings, trust channels, typed error codes, conformance levels, field-order governance, async workflow fixtures, and validator evidence.
Clearer transport fit
The current contract now publishes transport bindings so keyed and keyless JSON, accepted async responses, and trace context travel with named public guidance instead of local guesswork.
Trust without stack lock-in
UAI-1 now describes trust channels and companion credential expectations so teams can publish auditable identity posture without forcing one universal identity stack.
Better machine failure handling
The validator and UAI error flow now sit beside a public error registry and conformance ladder so failure handling and support claims are easier to automate responsibly.
Credible support boundaries
Implementations still scopes the real support boundary, but it now sits beside a much more complete protocol operating layer instead of carrying that burden alone.
That gives UAIX a clearer fit next to A2A, MCP, orchestration, tracing, and credential systems: those systems can keep their runtime roles while UAI-1 carries the portable public exchange and release record.
Launch Kit
Machine-facing surfaces for real implementation work
The public site now ships a route-level handbook, an OpenAPI export, and a reusable conformance packet so implementers can move from reading to automation without guessing at the live contract.
- API Reference Open Human-readable route handbook for discovery, schemas, validator runs, OpenAPI export, and conformance-pack assembly.
- OpenAPI JSON Open Machine-facing OpenAPI 3.1 export for the current UAIX REST surface.
- Conformance Pack Open Reusable packet of the current public schemas, registry records, fixtures, and launch pointers.
- Conformance Pack JSON Open Open the machine-readable release packet directly when launch review needs automation-friendly proof.
- Roadmap JSON Open Resolve priorities, normalization boundaries, metrics, and non-claims as a machine-readable planning record.
Trust Surface
Launch-stage policy and release posture
The launch story is stronger when trust posture is visible alongside the technical record. These pages now carry the current public answer on ownership, policy limits, and release discipline.
- Policy and Security Open Launch-stage public posture for licensing, privacy, accessibility, analytics, and security-sensitive release work.
- Governance Open See current authority posture, change discipline, and what remains future work instead of implied structure.
- References and Contributors Open Resolve the current public handoff packet, discovery links, attribution record, and citation path.
- Changelog Open Use the dated release trail when trust posture or support claims change between site updates.
- Roadmap Open Read the public future-work boundary before repeating planned interoperability claims.
How To Read It
Standards record first, platform story second
UAIX is the public standards site for UAI. UAI-1 is the current release. The site is strongest when readers can move quickly from a plain-language definition to the concrete proof surface: schemas, field-order governance, examples, validator output, support boundaries, and release history.
What it covers
A versioned public exchange contract for identity, conversation state, delivery semantics, trust metadata, payloads, outputs, and errors.
How to verify it
Read the spec, compare against the published examples and field registry, and run the validator before making support claims.
Who publishes it
Current published attribution: Michael Joseph Kappel, MCP. Use References and Contributors plus Governance for the public ownership and release record.
What it complements
UAI-1 complements orchestration, tool, and identity systems by standardizing the public exchange and release record instead of replacing every runtime protocol.
Example Exchange
A copyable, readable exchange record
{
"uai_version": "1.0",
"profile": "uai.intent.request.v1",
"message_id": "msg-2026-04-22-0001",
"source": {
"type": "agent",
"id": "agent.alpha",
"uri": "https://agents.alpha.example/runtime"
},
"target": {
"type": "service",
"id": "uaix.gateway",
"uri": "https://uaix.org/wp-json/uaix/v1/discovery"
},
"conversation": {
"conversation_id": "conv-2026-04-22-uaix-001",
"turn_id": "turn-001",
"traceparent": "00-4bf92f3577b34da6a3ce929d0e0e4736-00f067aa0ba902b7-01",
"sequence": 1
},
"delivery": {
"mode": "async",
"priority": "interactive",
"expires_at": "2026-04-22T16:05:00Z",
"reply_requested": true,
"ack_required": true
},
"trust": {
"channel": "credentialed",
"auth_scheme": "did+vc",
"principal": "did:web:agents.alpha.example",
"credential_ref": "https://agents.alpha.example/credentials/uai-interop.json",
"signature_ref": "https://agents.alpha.example/signatures/msg-2026-04-22-0001.jws",
"replay_window_id": "rw-2026-04-22-0001"
},
"body": {
"intent": "resolve-profile",
"subject": "uai.task.status.v1",
"requested_profile": "uai.task.status.v1",
"parameters": {
"include_field_registry": true
},
"constraints": [
"public-record-only",
"validator-ready"
],
"response_profile": "uai.intent.response.v1"
},
"provenance": {
"trace_id": "trace-7f3a2d",
"issued_at": "2026-04-22T16:00:00Z",
"log_ref": "urn:uaix:log:2026:0001",
"agent_id": "agent.alpha",
"model_id": "model.alpha.reasoner-2",
"confidence": 0.98
},
"integrity": {
"version": 2,
"algorithm": "sha256",
"canonicalization": "jcs",
"checksum": "sha256:dd8a9d16c9226cc9d1f4888a4d2bbcbf06b5b4b8"
},
"extensions": []
}
- profile Tells the validator which published UAI-1 message profile to apply.
- conversation Keeps multi-turn exchange state explicit instead of leaving workflow continuity implicit.
- delivery Declares sync versus async mode, priority, expiry, and acknowledgement expectations.
- trust.auth_scheme Makes the surrounding trust layer reviewable instead of assuming out-of-band identity context.
- provenance.trace_id Keeps the exchange tied to an auditable request and lineage trail.
- integrity.checksum Anchors the message to a reproducible, reviewable record.
[
"1.0",
"uai.intent.request.v1",
"msg-2026-04-22-0001",
[
"agent",
"agent.alpha",
null,
"https://agents.alpha.example/runtime"
],
[
"service",
"uaix.gateway",
null,
"https://uaix.org/wp-json/uaix/v1/discovery"
],
[
"conv-2026-04-22-uaix-001",
"turn-001",
null,
"00-4bf92f3577b34da6a3ce929d0e0e4736-00f067aa0ba902b7-01",
1
],
[
"async",
"interactive",
"2026-04-22T16:05:00Z",
true,
true
],
[
"credentialed",
"did+vc",
"did:web:agents.alpha.example",
"https://agents.alpha.example/credentials/uai-interop.json",
"https://agents.alpha.example/signatures/msg-2026-04-22-0001.jws",
"rw-2026-04-22-0001"
],
[
"resolve-profile",
"uai.task.status.v1",
"uai.task.status.v1",
{
"include_field_registry": true
},
[
"public-record-only",
"validator-ready"
],
"uai.intent.response.v1"
],
[
"trace-7f3a2d",
null,
"2026-04-22T16:00:00Z",
"urn:uaix:log:2026:0001",
"agent.alpha",
"model.alpha.reasoner-2",
0.98
],
[
2,
"sha256",
"jcs",
"sha256:dd8a9d16c9226cc9d1f4888a4d2bbcbf06b5b4b8"
],
[]
]
Field order follows the keyed JSON example, the published schema order, and the public field registry, which keeps compact transport aligned with the human-readable source record.
What Changed
The contract is deeper and more operational now
Async task visibility
UAI-1 now publishes a dedicated task-status profile so long-running work can stay on the public record instead of disappearing into private workflow state.
Field-order governance
Keyless transport stays usable because the public field registry now maps envelope order and profile body order explicitly.
Trust without lock-in
The envelope carries trust hints and replay-window metadata while leaving room for companion credential and transport systems.
Problem-details style errors
Errors are now richer, typed, and path-aware so downstream teams can react mechanically instead of parsing vague failure text.
Roadmap-backed boundaries
Future compact, bridge, validator, and developer-kit ideas now point to a public roadmap instead of living only in background notes.
Adoption Priority
Prioritize the teams publishing supportable machine-to-machine records
Cross-boundary agent handoffs
Adopt UAI-1 first when the exchange needs to travel between teams, services, or audit contexts without losing its meaning.
Runtime-plus-public contract stacks
Use it beside MCP, A2A, and local orchestrators when runtime coordination is already solved but the public exchange still needs a portable record.
Async, regulated, or review-heavy flows
Prioritize UAI-1 when teams need explicit provenance, typed failures, trust posture, or task-state visibility before a workflow can be called supportable.
Release-ready implementation programs
Start here when a public implementation needs validator evidence, a conformance packet, and a named release lane before wider ecosystem claims are made.
Roadmap-governed expansion
Use the roadmap to decide when A2A, MCP, compact-transfer, SDK, CLI, or binary-envelope ideas have enough public proof to move forward.