Intelligence API
Part of CLPI Phase 3: Intelligence Layer. The Intelligence API provides fault line analysis, risk forecasting, and policy recommendations.
https://api.mnemom.ai/v1
Authentication
All intelligence endpoints require API key authentication.
API key authentication: Pass in the
Authorization header:
POST /v1/api-keys.
Rate limits
Rate-limited responses return HTTP
429 with a Retry-After header.
LLM-powered endpoints (
recommend-policy, forecast) have lower limits due to compute cost.Endpoints
POST /v1/teams/fault-lines
Analyze fault lines in a team’s configuration — value conflicts, capability gaps, and agent incompatibilities. Request body:
Response:
200 OK
FaultLine object:
FaultLineClassification enum:
Severity levels:
Summary object:
FaultLineAlignment object:
The fault line analysis is grounded in the
checkFleetFaultLines function from @mnemom/agent-alignment-protocol. The same analysis is reproducible locally without the API.POST /v1/teams/forecast
Forecast risks based on fault line analysis. Uses LLM analysis (Claude Haiku) to predict failure modes and their probabilities. Request body:
Response:
200 OK
FailureMode object:
FailureMode types:
Error responses:
POST /v1/teams/recommend-policy
Generate a policy recommendation based on team analysis. Uses LLM analysis to produce a policy that resolves detected fault lines and mitigates forecasted risks. Request body:
Response:
200 OK
ReasoningStep object:
ForecastSummary object:
Validation object:
Error responses:
POST /v1/transactions
Create a transaction with scoped guardrails. Transaction guardrails use a 3-layer merge: org + team + transaction policies with intersection semantics forcapability_mappings.
Request body:
Response:
201 Created
Error responses:
GET /v1/transactions/
Get transaction details including the resolved policy. Parameters:
Response:
200 OK
Returns the same transaction object as POST /v1/transactions.
Error responses:
DELETE /v1/transactions/
Delete or cancel an active transaction. Expired transactions are automatically cleaned up and do not need to be deleted. Parameters:
Response:
204 No Content
Error responses:
Error codes
All error responses follow the standard envelope:
SDK usage
The Intelligence endpoints are not yet wrapped by the
@mnemom/sdk client (which currently covers the agents and catalog namespaces). Call them directly over HTTP until SDK helpers ship.See also
- Policy Engine — Policy concepts
- Team Reputation — Team scoring
- Policy Management — Policy workflows
- Risk Engine Guide — Risk assessment