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

Tools

Conformance Pack

Reusable machine-readable packet for the current public UAI-1 record, validator evidence path, and launch-review inventory.

  • Record UAIX-TOOL-0065
  • Path /es-us/tools/conformance-pack/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-TOOL-0065
Surface
Tools
Access
Public and linkable

How to use this page

Use this page to assemble the current reusable conformance packet for launch review and release evidence.

Evidence sources

Conformance Pack JSONAdoption KitValidatorImplementations

Evidence Packet

What travels into launch review and support claims

The conformance pack keeps the current public record, implementation evidence checklist, and conformance fixture pack together for reuse. Treat it as the evidence bundle behind release review, not as a certification surface by itself.

What travels

Catalog, schemas, fixtures, checklist, regression cases, and trust records

The pack carries the public standards inventory, implementation evidence checklist, conformance fixture pack, and machine-readable supporting records another reviewer needs to reconstruct the same baseline.

When to attach it

Launch review, regression, and release notes

Use the pack when validation evidence, fixture expectations, and checklist answers need to travel into implementation review, packaging checks, or a dated public release record.

What not to claim

Evidence is not certification

A pack helps prove what was checked, but it does not create a badge, endorsement, or blanket support claim on its own.

Evidence sources

Conformance Pack JSONMachine-readable release packet.Adoption KitPublished first-proof bundle before the broader evidence packet.ValidatorGenerate the result that belongs in the packet.ImplementationsAttach the packet to the named release lane.Policy and SecurityTrust posture that frames the packet.

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.
Pack endpointsFetch or download the current packet
curl -s https://uaix.org/wp-json/uaix/v1/conformance-pack
curl -OJ "https://uaix.org/wp-json/uaix/v1/conformance-pack?download=1"

Use the raw JSON route for automation and the download form when the exact packet needs to travel as an attachment.

What this pack is

The UAIX conformance pack is the reusable machine-readable release packet for the current public UAI-1 record. It keeps the catalog, discovery manifest, schemas, registry, field order, examples, guidance records, roadmap record, implementation-evidence checklist, conformance fixture pack, and pack-level launch pointers together so another reviewer can reconstruct the same public baseline without private notes.

What belongs in the pack

  • The current catalog and discovery surface.
  • The active schema, registry, field-registry, example, transport, trust, conformance, error, and roadmap records.
  • The public entry points for the validator, API reference, roadmap, and current launch-support pages.
  • An implementation-evidence checklist for implementation identity, supported profile scope, validator evidence, machine-route and cache posture, trust and threat boundary, locale/accessibility reader QA, fixtures, release trail, and support boundary.
  • A conformance fixture pack with positive keyed, minified-keyed, and keyless checks, canonical-hash equivalence metadata, and negative current-boundary cases for schema, trace, trust, keyless-shape, keyless-overflow, and unsupported-alias behavior.
  • A quickstart sequence for turning one published profile into a reviewable release packet.

How teams should use it

  1. Start with one profile and one validator-backed proof run.
  2. Run the fixture pack and complete the implementation-evidence checklist before describing the result as a release-ready support claim.
  3. Attach the pack when that proof needs to travel into implementation review, launch QA, or release evidence.
  4. Keep the pack aligned with Implementations, the Changelog, News, and the Roadmap whenever public support posture changes.
  5. Do not describe the pack itself as a certification or badge program; it is the reusable evidence packet behind those future-facing ideas.

When to rerun the pack

  • Rerun it when schemas, registry entries, field order, examples, validator policy, transport guidance, trust-channel wording, error codes, implementation version, public route headers, or support language changes.
  • Rerun it before turning private QA evidence into a public support claim, migration note, implementation page, or release announcement.
  • Rerun it when a bridge, plugin, package, or consuming site changes the way it maps UAI-1 records into runtime behavior.

What the pack cannot prove by itself

  • It is not certification, endorsement, compliance approval, production availability evidence, security review, privacy review, or a guarantee that future UAI-1 changes will remain compatible.
  • It does not replace implementation-specific tests, threat modeling, accessibility checks, localization review, operational monitoring, or release rollback planning.
  • It must stay attached to a named implementation scope, dated release trail, and explicit non-claims.

Live reusable release packet

Use the published pack below when you want the current JSON bundle, fixture expectations, and profile-by-profile inventory that go with it.

Conformance pack

Reusable release packet

This pack assembles the current public release artifacts into one machine-readable packet for onboarding, regression checks, implementation review, and pre-launch release evidence.

What ships together

Core public release artifacts

  • Catalog and discovery manifest
  • Registry, schemas, field registry, and published examples
  • Transport, trust, conformance, and error guidance
  • Validator and API-reference entry points for repeatable checks

Best use

Ship one reviewable packet

Carry one pack alongside validator output, implementation evidence, and the changelog or release note so another reviewer can reconstruct the same public record without private context.

Release sequence

How to use the pack before launch

  1. Resolve the catalog and discovery routes first so the release packet points at the current public record.
  2. Choose one published profile, then pair its schema, registry entry, example fixture, field-order guidance, and validator normalization mode before validation.
  3. Run the validator and keep the exported conformance result beside the exact artifact URLs used during the check.
  4. Complete the implementation evidence checklist with implementation identity, supported profiles, artifact references, validator output, release trail, and support boundary.
  5. Run the capability-adaptive L0-L6 fixtures before claiming limited-browser, structured-fetch, browser-assisted, tool-agent, workflow-agent, multi-agent-runtime, or audited-agent-system support.
  6. Run the conformance fixture pack so positive keyed/minified/keyless cases, canonical-hash equivalence, and negative schema, trace, trust, keyless-shape, keyless-overflow, and unsupported-alias cases stay reproducible before release.
  7. Review the bridge evidence pack when A2A, MCP, OpenAPI, DID/VC, or Trace Context claims need concrete UAI-1 mapping examples without becoming replacement claims.
  8. Complete the principles impact assessment when a change affects cognitive liberty, AI memory, agent communication, capability description, handoff structure, privacy, accessibility, analytics, support claims, or public trust posture.
  9. Attach the validator result, implementation-track evidence, changelog link, and release-note link before making a public support claim.

UAI-REGI-0001

UAI Intent Request v1

Request an explicit outcome or async task against a declared subject using the full UAI-1 envelope, trust metadata, and reviewable delivery controls.

Profile
uai.intent.request.v1
Expected status
PASS
Required body fields
intent, subject, requested_profile, parameters, constraints, response_profile
Schema Example Registry

UAI-REGI-0002

UAI Intent Response v1

Return a direct result or accepted-task handoff for a declared request while preserving conversation continuity, trust metadata, and release-ready evidence.

Profile
uai.intent.response.v1
Expected status
PASS
Required body fields
status, subject, request_message_id, result, notices
Schema Example Registry

UAI-REGI-0003

UAI Capability Statement v1

Publish capability, endpoint, security, async workflow, and extension-support metadata so adjacent systems can resolve what an implementation actually supports.

Profile
uai.capability.statement.v1
Expected status
PASS
Required body fields
capability_id, version, operations, input_profiles, output_profiles, async_profiles, security_schemes, endpoints
Schema Example Registry

UAI-REGI-0004

UAI Error v1

Report validation, transport, authorization, or execution failures using a typed problem-details-style envelope with retry and path-level detail.

Profile
uai.error.v1
Expected status
PASS
Required body fields
type, title, detail, status, code, uaixCode, uaixCategory, uaixSeverity, retryable, instance, documentationUrl, traceId, correlationId, evidenceRecommended, suspensionRecommended, redactionApplied
Schema Example Registry

UAI-REGI-0005

UAI Conformance Result v1

Capture validator output, artifact references, and issue summaries in the same public message family so proof can travel with the release record.

Profile
uai.conformance.result.v1
Expected status
PASS
Required body fields
status, checked_profile, issues, summary, artifacts
Schema Example Registry

UAI-REGI-0006

UAI Task Status v1

Publish long-running task state, progress, blockers, and result references so async agent work stays auditable instead of disappearing into private workflow state.

Profile
uai.task.status.v1
Expected status
PASS
Required body fields
task_id, state, subject, progress, status_message
Schema Example Registry

UAI-AGENT-0001

UAI Agent Message v1

Canonical UAI-1 envelope packet for informational, directive, or query agent communication with context references, acknowledgement requirements, idempotency, correlation, and support boundaries.

Profile
uai.agent.message.v1
Expected status
PASS
Required body fields
message_type, content, context_refs, requires_acknowledgement, intent_semantics, execution_constraints, support_boundary
Schema Example Registry

UAI-AGENT-0002

UAI Agent Acknowledgement v1

Canonical UAI-1 envelope acknowledgement packet for receipt, parsing, validation, rejection, and acknowledgement-loop closure.

Profile
uai.agent.ack.v1
Expected status
PASS
Required body fields
acknowledged_message_id, status, received_at_utc, closes_acknowledgement_loop, support_boundary
Schema Example Registry

UAI-AGENT-0003

UAI Agent Task Status v1

Canonical UAI-1 envelope status packet for task progress, current action, UTC estimates, and correlation-linked workflow evidence while execution remains outside UAIX.

Profile
uai.agent.task-status.v1
Expected status
PASS
Required body fields
task_id, state, percent_complete, current_action, support_boundary
Schema Example Registry

UAI-AGENT-0004

UAI Agent Blocker v1

Canonical UAI-1 envelope blocker packet for authorization, resource, ambiguity, system, context, unsupported-capability, validation, secret, destructive-action, or boundary-conflict review.

Profile
uai.agent.blocker.v1
Expected status
PASS
Required body fields
blocker_id, blocker_type, description, human_review_required, support_boundary
Schema Example Registry

UAI-AGENT-0005

UAI Agent Memory Proposal v1

Canonical UAI-1 envelope memory proposal packet for reviewed candidate facts, source type, pending-review promotion status, secret rejection, and execution separation.

Profile
uai.agent.memory-proposal.v1
Expected status
PASS
Required body fields
proposal_id, source_type, proposed_facts, proposed_status, task_execution_separation, support_boundary
Schema Example Registry

UAI-AGENT-0006

UAI Agent Handoff v1

Canonical UAI-1 envelope handoff packet for task transfer, target agent, context summary, reason, exact next action, and safe delegated authorization references.

Profile
uai.agent.handoff.v1
Expected status
PASS
Required body fields
task_id, target_agent_id, context_summary, handoff_reason, exact_next_action, support_boundary
Schema Example Registry

UAI-AGENT-0007

UAI Agent Final Report v1

Canonical UAI-1 envelope final report packet requiring task summary, changed and new files, tests, skipped checks, blockers, risks, validation evidence, memory decisions, and exact next action.

Profile
uai.agent.final-report.v1
Expected status
PASS
Required body fields
task_id, summary, files_changed, new_files, tests_run, skipped_checks, blockers, risks, validation_evidence, memory_updates_proposed, memory_updates_skipped, exact_next_action, support_boundary
Schema Example Registry

UAI-AGENT-0008

UAI Agent Correction v1

Canonical UAI-1 envelope correction packet that preserves immutable history by naming the original message, correction reason, changed summary, and corrected fields or revised payload.

Profile
uai.agent.correction.v1
Expected status
PASS
Required body fields
original_message_id, correction_reason, changed_summary, support_boundary
Schema Example Registry

UAI-CAP-0001

UAI Capability Profile v1

Canonical UAI-1 envelope declaring a client's capability level, safe fallbacks, consent boundaries, known limits, recommended UAIX profiles, and evidence requirements.

Profile
uai.capability.profile.v1
Expected status
PASS
Required body fields
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
Schema Example Registry

UAI-CAP-0002

UAI Capability Negotiation v1

Canonical UAI-1 envelope for selecting the safest supported client level and preserving unsupported features, fallback behavior, consent boundaries, and evidence requirements.

Profile
uai.capability.negotiation.v1
Expected status
PASS
Required body fields
negotiation_id, requested_client_level, observed_client_level, selected_client_level, selected_profile, requested_operation, unsupported_features, fallback_behavior, consent_boundaries, evidence_requirements, recommended_uaix_profiles, safe_default_response, support_boundary
Schema Example Registry

UAI-CAP-0003

UAI Limited Browser Client v1

L0 client capability profile for static text, static HTML, Markdown, sitemap, llms.txt, and JSON fetch support without JavaScript, browser UI, authentication, posting, tools, memory, or coordination.

Profile
uai.client.limited-browser.v1
Expected status
PASS
Required body fields
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
Schema Example Registry

UAI-CAP-0004

UAI Structured Fetch Client v1

L1 client capability profile for structured static and JSON fetch with low-token machine routes and explicit no-JavaScript fallbacks.

Profile
uai.client.structured-fetch.v1
Expected status
PASS
Required body fields
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
Schema Example Registry

UAI-CAP-0005

UAI Browser-Assisted Client v1

L2 client capability profile for JavaScript rendering and human-visible browser assistance with parity checks and no autonomous write authority.

Profile
uai.client.browser-assisted.v1
Expected status
PASS
Required body fields
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
Schema Example Registry

UAI-CAP-0006

UAI Tool Agent Client v1

L3 client capability profile for tool-calling agents that can authenticate or post only with consent, idempotency, fallback, and evidence records.

Profile
uai.client.tool-agent.v1
Expected status
PASS
Required body fields
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
Schema Example Registry

UAI-CAP-0007

UAI Workflow Agent Client v1

L4 client capability profile for long-running workflow agents that preserve task status, correlation, timeout, idempotency, fallback, consent, and final-report evidence.

Profile
uai.client.workflow-agent.v1
Expected status
PASS
Required body fields
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
Schema Example Registry

UAI-CAP-0008

UAI Multi-Agent Runtime Client v1

L5 client capability profile for external multi-agent runtimes that coordinate agents while UAIX remains the reviewed record, trust, memory, evidence, and handoff boundary.

Profile
uai.client.multi-agent-runtime.v1
Expected status
PASS
Required body fields
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
Schema Example Registry

UAI-CAP-0009

UAI Audited Agent System Client v1

L6 client capability profile for high-assurance agent systems that attach provenance, audit evidence, consent records, validator output, memory review, and final-report evidence.

Profile
uai.client.audited-agent-system.v1
Expected status
PASS
Required body fields
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
Schema Example Registry

UAIX-ACF-6200

UAIX Ability Profile v1

UAIX Ability Profile v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.ability-profile.v1
Expected status
PASS
Required body fields
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Schema Example Registry

UAIX-ACF-6201

UAIX Startup Packet v1

UAIX Startup Packet v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.startup-packet.v1
Expected status
PASS
Required body fields
startup_packet_id, read_order, domain_boundaries, first_acceptable_response, no_op_triggers, validation_targets, identity, token_custody, discovery_bootstrap, safe_harbor, utc_requirements
Schema Example Registry

UAIX-ACF-6201B

UAIX Next Recursive Prompt v1

Derived hot-memory resume artifact required for agents that deal with code, automation, executable workflows, or code-like artifacts. It is not required for agents that don't deal with any coding.

Profile
uaix.next-recursive-prompt.v1
Expected status
PASS
Required body fields
Schema Example Registry

UAIX-ACF-6202

UAIX Suspension Packet v1

UAIX Suspension Packet v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.suspension-packet.v1
Expected status
PASS
Required body fields
suspension_packet_id, state_summary, checks_run, checks_skipped, blockers, next_safe_step, network_obstruction, retry_policy, evidence_packet, human_escalation
Schema Example Registry

UAIX-ACF-6203

UAIX Receiver Brief v1

UAIX Receiver Brief v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.receiver-brief.v1
Expected status
PASS
Required body fields
receiver_brief_id, read_order, first_acceptable_response, domain_boundaries, escalation_triggers, no_op_triggers
Schema Example Registry

UAIX-ACF-6204

UAIX Memory Firewall Policy v1

UAIX Memory Firewall Policy v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.memory-firewall-policy.v1
Expected status
PASS
Required body fields
policy_id, quarantine_default, adoption_requirements, blocked_requests, no_op_triggers, human_review_required
Schema Example Registry

UAIX-ACF-6205

UAIX No-Op Trigger Catalog v1

UAIX No-Op Trigger Catalog v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.no-op-trigger-catalog.v1
Expected status
PASS
Required body fields
catalog_id, triggers, default_response, human_review_url, forbidden_recovery
Schema Example Registry

UAIX-ACF-6206

UAIX Authority Boundary v1

UAIX Authority Boundary v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.authority-boundary.v1
Expected status
PASS
Required body fields
matrix_id, boundaries, not_authorized_for, no_op_triggers, safe_quote_summary
Schema Example Registry

UAIX-ACF-6207

UAIX Conformance Evidence v1

UAIX Conformance Evidence v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.conformance-evidence.v1
Expected status
PASS
Required body fields
evidence_id, profile_id, schema_url, fixture_url, checks, result, limitations
Schema Example Registry

UAIX-ACF-6208

UAIX Evaluation Packet Summary v1

UAIX Evaluation Packet Summary v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.evaluation-packet-summary.v1
Expected status
PASS
Required body fields
summary_id, packet_profiles, required_levels, no_op_triggers, limitations
Schema Example Registry

UAIX-ACF-6209

UAIX Ability Profile L0 v1

UAIX Ability Profile L0 v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.ability-profile.l0.v1
Expected status
PASS
Required body fields
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Schema Example Registry

UAIX-ACF-6210

UAIX Ability Profile L1 v1

UAIX Ability Profile L1 v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.ability-profile.l1.v1
Expected status
PASS
Required body fields
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Schema Example Registry

UAIX-ACF-6211

UAIX Ability Profile L2 v1

UAIX Ability Profile L2 v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.ability-profile.l2.v1
Expected status
PASS
Required body fields
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Schema Example Registry

UAIX-ACF-6212

UAIX Ability Profile L3 v1

UAIX Ability Profile L3 v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.ability-profile.l3.v1
Expected status
PASS
Required body fields
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Schema Example Registry

UAIX-ACF-6213

UAIX Ability Profile L4 v1

UAIX Ability Profile L4 v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.ability-profile.l4.v1
Expected status
PASS
Required body fields
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Schema Example Registry

UAIX-ACF-6214

UAIX Ability Profile L5 v1

UAIX Ability Profile L5 v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.ability-profile.l5.v1
Expected status
PASS
Required body fields
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Schema Example Registry

UAIX-ACF-6215

UAIX Ability Profile L6 v1

UAIX Ability Profile L6 v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.ability-profile.l6.v1
Expected status
PASS
Required body fields
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Schema Example Registry

UAIX-ACF-6216

UAIX Expression-Concept Review v1

UAIX Expression-Concept Review v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.evaluation.expression-concept-review.v1
Expected status
PASS
Required body fields
source_expression, concept_boundary, interpretation, confidence, no_op_triggers
Schema Example Registry

UAIX-ACF-6217

UAIX Resource-Economy Trace v1

UAIX Resource-Economy Trace v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.evaluation.resource-economy-trace.v1
Expected status
PASS
Required body fields
resource_scope, cost_model, limits, evidence_refs, no_op_triggers
Schema Example Registry

UAIX-ACF-6218

UAIX Operator Decision v1

UAIX Operator Decision v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.evaluation.operator-decision.v1
Expected status
PASS
Required body fields
decision, authority_basis, options_reviewed, human_review_required, no_op_triggers
Schema Example Registry

UAIX-ACF-6219

UAIX No-op Justification v1

UAIX No-op Justification v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.evaluation.no-op-justification.v1
Expected status
PASS
Required body fields
trigger, reason, missing_evidence, human_review_url, safe_next_step
Schema Example Registry

UAIX-ACF-6220

UAIX Local Sandbox Safety Review v1

UAIX Local Sandbox Safety Review v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.evaluation.local-sandbox-safety-review.v1
Expected status
PASS
Required body fields
sandbox_scope, unsafe_requests, blocked_operations, review_result, no_op_triggers
Schema Example Registry

UAIX-ACF-6221

UAIX Memory Ecosystem Handoff v1

UAIX Memory Ecosystem Handoff v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.evaluation.memory-ecosystem-handoff.v1
Expected status
PASS
Required body fields
source_memory, quarantine_status, promotion_targets, conflicts, receiver_brief
Schema Example Registry

UAIX-ACF-6222

UAIX DE11 Benchmark Summary v1

UAIX DE11 Benchmark Summary v1 for the UAIX agent capability, memory firewall, evaluation packet, and conformance evidence surface.

Profile
uaix.evaluation.de11-benchmark-summary.v1
Expected status
PASS
Required body fields
benchmark_id, bounded_scope, reference_result, limitations, non_claims
Schema Example Registry

UAIX-SPEC-0101

UAIX SPEC-01 Canonical Envelope v1

Publication-envelope contract for portable evidence-bearing UAIX records, including payload, evidence, redaction, trust, signature status, verification, exceptions, and warnings.

Profile
uaix.spec-01.envelope.v1
Expected status
PASS
Required body fields
uaixVersion, spec, envelopeId, createdUtc, issuer, issuerDisplayName, issuerPublicUrl, issuerCapabilityLevel, audience, lifecycleState, trustPosture, payloadType, payloadSchema, payload, evidence, redactions, signature, signatureStatus, verification, exceptions, warnings, rules, supportBoundary, localPolicyWins
Schema Example Registry

UAIX-CAPSTD-0101

UAIX Capability Profile v1

UAIX capability profile for declaring L0-L6 client posture, consent boundaries, fallback behavior, evidence requirements, and safe default behavior.

Profile
uaix.capability-profile.v1
Expected status
PASS
Required body fields
capabilityProfileId, profileVersion, declaredLevel, supportedLevels, capabilities, consentRequiredFor, fallbacks, safeDefaultResponse, evidenceRequirements, supportBoundary, localPolicyWins
Schema Example Registry

UAIX-CAPSTD-0102

UAIX Capability Ladder v1

Machine-readable L0-L6 capability ladder with safe fallbacks, unsupported implication boundaries, and reference-only client scenarios.

Profile
uaix.capability-ladder.v1
Expected status
PASS
Required body fields
ladderId, levels, fallbackRules, safeDefaultResponse, referenceExamples, supportBoundary, localPolicyWins
Schema Example Registry

UAIX-SPEC-0201

UAIX SPEC-02 Project Handoff v1

Portable project memory and custody transfer contract for humans, agents, vendors, future sessions, and reviewed runtime consumers.

Profile
uaix.spec-02.project-handoff.v1
Expected status
PASS
Required body fields
projectId, handoffId, createdUtc, owner, custodian, frontDoor, memoryRoots, requiredReads, currentState, constraints, decisions, nextActions, targetedChecks, evidence, redactions, warnings, referenceScenarios, supportBoundary, localPolicyWins
Schema Example Registry

UAIX-SPEC-0301

UAIX SPEC-03 AGENTS.md Metadata v1

AGENTS.md front-door metadata for canonical roots, nested instruction scope, command policy, memory loading, and safety boundaries.

Profile
uaix.spec-03.agents-md-metadata.v1
Expected status
PASS
Required body fields
repositoryId, canonicalRoot, agentsMdPath, coordinatorPath, localUaiRoot, nestedScopes, requiredReads, commandPolicy, forbiddenOperations, memoryPolicy, securityBoundaries, examples, supportBoundary, localPolicyWins
Schema Example Registry

UAIX-SPEC-0401

UAIX SPEC-04 File Handoff v1

Safe supplied-file intake contract for manifests, bucket review, disposition, redaction, evidence, lifecycle, blocked-file rules, and archives.

Profile
uaix.spec-04.file-handoff.v1
Expected status
PASS
Required body fields
handoffId, createdUtc, intakeBuckets, fileManifest, reviewDispositions, redactionPolicy, lifecycle, archivePolicy, evidence, blockedFileRules, supportBoundary, localPolicyWins
Schema Example Registry

UAIX-REVIEW-0101

UAIX Review Receipt v1

Review receipt for inspected UAIX envelopes, checks, skipped checks, warnings, exceptions, trust decision, and local-policy result.

Profile
uaix.review-receipt.v1
Expected status
PASS
Required body fields
receiptId, reviewedEnvelopeId, reviewedUtc, reviewer, reviewResult, checksRun, checksSkipped, warnings, exceptions, trustDecision, supportBoundary, localPolicyWins
Schema Example Registry

UAIX-AUDIT-0101

UAIX Public-Safe Audit Digest v1

Public-safe audit digest for evidence references, redactions, public findings, excluded private material, verification, exceptions, and warnings.

Profile
uaix.public-safe-audit-digest.v1
Expected status
PASS
Required body fields
digestId, subject, createdUtc, scope, evidenceRefs, redactions, publicFindings, privateMaterialExcluded, verification, exceptions, warnings, supportBoundary, localPolicyWins
Schema Example Registry

UAIX-REDACT-0101

UAIX Redaction Policy v1

Redaction policy for secret patterns, data classes, review gates, never-publish values, verification, exceptions, and warnings.

Profile
uaix.redaction-policy.v1
Expected status
PASS
Required body fields
policyId, createdUtc, appliesTo, secretPatterns, dataClasses, redactionActions, reviewRequiredFor, neverPublish, verification, exceptions, warnings, supportBoundary, localPolicyWins
Schema Example Registry

Reusable packet

How the conformance pack fits into launch readiness

Use this map when the downloadable pack needs human-facing release context and honest support-claim language around it.

Stage 1

Validated packet

A published fixture or candidate message passed against the current public record.

  • Useful for review, debugging, and regression work right away.
  • Still evidence only until the result is attached to a named release lane.

Stage 2

Release-ready packet

The passing result now travels with implementation versioning, artifact links, and discovery context.

  • Keep the checked packet, validator export, artifact URLs, and compatibility notes together.
  • This is the handoff point for launch review, packaging, and repeatable QA.

Stage 3

Public support claim

The named implementation track and release trail now say what is publicly supported and what is still out of scope.

  • Scope the claim to the exact profiles, transport bindings, and owner path that are actually published.
  • Use the current conformance level and release links so another reader can verify the same state.

Pack contents

What the reusable machine packet already carries

  • The current release packet already carries 56 profiles, 56 schemas, and 56 examples from the live public record.
  • Catalog, discovery, field-order, transport, trust, conformance, and error guidance in one JSON handoff.
  • Validator and API-reference entry points for repeatable launch review and automation.
  • A quickstart path for turning one published profile into a reviewable release packet.

Human release context

What the pack still needs from the public site

  • Implementation version, owner path, and the exact support boundary being claimed.
  • Changelog or news links that explain what changed in this release.
  • Policy and Security posture when the release changes trust-significant behavior.
  • Conformance-level language that keeps the outward-facing claim narrower than the packet itself.

Current public conformance levels: Use these levels for outward-facing language once the packet becomes part of a named release and implementation record.

L1-core-envelope

L1 Core Envelope

Produce or consume keyed UAI envelopes for named profiles without changing the canonical root fields.

  • Preserve uai_version, profile, message_id, source, target, conversation, delivery, trust, body, provenance, integrity, and extensions.
  • Name the exact profile and release for every support claim.
  • Do not claim runtime execution from envelope support alone.

Public claim: May claim L1 only for the exact named profiles whose canonical envelope round-trips successfully.

L2-profile-validation

L2 Profile Validation

Pass published schema and validator checks for the exact profiles claimed.

  • Resolve schemas, registry entries, examples, and field registry records from public UAIX routes.
  • Pass positive fixtures and fail required negative fixtures for each claimed profile.
  • Keep skipped checks and validator warnings attached to evidence.

Public claim: May claim L2 only for profiles with validator-backed evidence.

L3-trust-and-integrity

L3 Trust and Integrity

Preserve trust metadata, replay-window hints, provenance, integrity, and trace continuity.

  • Declare trust channel and principal.
  • Preserve integrity canonicalization and checksum metadata.
  • Validate signed, credentialed, did+vc, and trace metadata when claimed.

Public claim: May claim L3 only for the trust channels and integrity behavior proven by fixtures.

L4-public-record-publisher

L4 Public Record Publisher

Publish discoverable public artifacts needed for external inspection and reproduction.

  • Publish discovery, schemas, registry, examples, field registry, transport bindings, trust channels, error registry, conformance levels, validator guidance, changelog, and release evidence.
  • Keep sitemap, llms.txt, and public navigation aligned with current routes.
  • Avoid private logs or screenshots as the only support evidence.

Public claim: May claim L4 only for the public release surface that is discoverable and evidenced.

L5-agent-communication-profiles

L5 Agent Communication Profiles

Support the eight uai.agent.*.v1 profiles as canonical UAI-1 envelope records.

  • Validate agent message, ack, task-status, blocker, memory-proposal, handoff, final-report, and correction profiles.
  • Reject secret-like memory proposals, unsafe blockers, cold-memory direct promotion, and incomplete final reports.
  • Carry the UAIX support boundary in relevant records.

Public claim: May claim L5 only for the specific agent profiles with passing positive and negative conformance cases.

L6-reliable-delegation-idempotency-correlation

L6 Reliable Delegation with Idempotency and Correlation

Use idempotency, correlation, retry, lifecycle, timeout, fallback, acknowledgement, and expected-output rules for delegated work.

  • Require delivery.idempotency_key for each distinct delegated or destructive operation.
  • Preserve conversation.correlation_id across related messages.
  • Declare retry_count, sequence, expires_at, lifecycle, timeout_ms, fallback_directive, and expected_output_schema when delegation is claimed.

Public claim: May claim L6 only for reliable delegation behavior proven by conformance fixtures and receiver behavior.

L7-capability-negotiation

L7 Capability Negotiation

Publish and validate capability discovery, assertions, negotiation failures, and unsupported-capability responses.

  • Publish capability statements with exact profiles, bindings, trust channels, conformance levels, and error codes.
  • Return capability_not_supported for unsupported capability requests.
  • Do not imply certification, official adapter status, hosted messaging, or runtime orchestration.

Public claim: May claim L7 only for the exact capability negotiation flows proven by public fixtures and validator behavior.

Claim rules

Public language should stay inside published evidence

  • Support claims must name the highest achieved level plus the exact profiles, transport bindings, trust channels, and conformance cases implemented.
  • A project may claim only profiles, bindings, trust channels, and conformance levels that public fixtures and validator tests prove.
  • A passing validator result is evidence, not certification, endorsement, official adapter support, hosted messaging, automatic sync, or runtime execution.
  • Public-record claims require discoverable schemas, registry records, examples, field registry records, error codes, conformance pack cases, changelog, and release notes.
  • Revalidate support claims when schemas, registry records, field order, examples, validator behavior, implementation version, trust posture, sitemap, or public navigation changes.
  • Conformance evidence does not prove security, privacy, availability, performance, legal compliance, hosted trust infrastructure, or production operations by itself.
  • Keep the implementation page, release trail, and citation/discovery links attached when another team needs to verify the same public state.

Working rule: Use the conformance ladder for language, but use the named implementation track and release trail for the actual public support boundary.

Conformance Pack API Reference Policy and Security Validator Open conformance JSON References and Contributors

Next step

Continue to Policy and Security for the current public trust posture, return to API Reference when you need the route-level machine contract behind the pack, or open the Roadmap when a support claim depends on future-work boundaries.

Capability-adaptive web interaction records

The 3.56.0 release adds the L0-L6 client capability ladder, nine capability profile IDs, validator rules for fallback/consent/idempotency/correlation/evidence/boundary failures, and adoption-kit starter files.

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.