REST
Stable HTTPS contracts
Approved systems read Planetary Model context packets, evidence bundles, decision inputs, and updates through versioned JSON contracts.
AgentLayer machine contract
Protocol access for governed AI agent context.
CrowdAlpha Protocol is the machine contract inside AgentLayer. It lets authorized agents and software systems request evidence-linked Planetary Model context, decision inputs, and subscribed updates through REST, MCP, A2A, and SDKs.
MCP
Agent tool access
MCP tools wrap the same read contracts so agents can request grounded context and discovery leads without scraping pages or inventing state.
A2A
Agent-to-agent calls
A2A discovery and message calls expose selected AgentLayer skills with the same scopes, redaction, and no-mutation rules.
SDKs
Typed client helpers
TypeScript and Python clients preserve envelopes, schema names, evidence references, uncertainty, and access metadata.
The protocol is read-first. It returns uncertainty, redaction, and access metadata when state is missing or not available to the caller.
Protocol rules
Built for agents without giving agents the keys to state.
Read-first
Agents request stored context, evidence, discovery findings, and decision inputs before downstream action.
Evidence-linked
Responses carry source references, provenance, confidence, uncertainty, and audit context.
Scoped
Access is governed by approved clients, scopes, entitlements, redaction, and rate limits.
No state mutation
Agents do not write directly into the Planetary Model through the protocol.
Response shape
A protocol response carries the read and the conditions around the read.
Public examples stay intentionally sanitized. Production responses preserve enough metadata for approved systems to know what was read, what evidence supports it, whether anything was redacted, and whether the caller is allowed to use it.
Sanitized envelope
{
"success": true,
"data": {
"schemaVersion": "crowdalpha.agent.v1",
"asOf": "2026-05-05T18:00:00Z",
"answerType": "grounded_world_context",
"status": "READY",
"entity": {
"entityId": "CROWDALPHA_ENTITY_ID",
"state": "CONSTRAINED"
},
"confidence": 0.77,
"uncertainty": 0.18,
"evidence": [
{
"evidenceId": "observation:CROWDALPHA_EVIDENCE_ID",
"observationId": "CROWDALPHA_EVIDENCE_ID",
"type": "world_observation",
"collectedAt": "2026-05-05T17:52:00Z"
}
],
"provenance": {
"interface": "crowdalpha_agent_interface_v1",
"truthLayer": "world_model",
"authority": "stored_worldstate_record",
"llmGeneratedFactsAllowed": false
},
"interfaceProvenance": {
"interface": "crowdalpha_agent_interface_v1",
"truthLayer": "world_model",
"authority": "stored_worldstate_record",
"llmGeneratedFactsAllowed": false
},
"redaction": {
"applied": false,
"rules": []
},
"entitlements": {
"mode": "agent_client_v1",
"requiredScopes": [
"world.read",
"evidence.read"
],
"effectiveScopes": [
"world.read",
"evidence.read"
],
"missingScopes": []
}
}
}Agent flow
The agent reads, verifies, then carries the receipt.
01
Identify the entity, package, or workflow.
02
Ask what stale assumption, missing evidence, or hidden exposure may be costly.
03
Read current Planetary Model state through an approved AgentLayer contract.
04
Inspect uncertainty, redaction, and evidence references.
05
Fetch evidence or decision inputs before citing the result.
06
Carry provenance and audit metadata into the downstream workflow.