---
title: "Assess risk for a team of agents"
method: POST
path: "/risk/assess/team"
tags: ["Risk"]
---

# Assess risk for a team of agents

`POST /risk/assess/team`

## Request

- Base URL: `https://api.mnemom.ai/v1`
- URL: `https://api.mnemom.ai/v1/risk/assess/team`
- Auth: HTTP bearer

Compute a team-level risk assessment given an explicit `agent_ids` list (or a `team_id` to resolve the roster). Produces three-pillar results: portfolio, coherence, concentration, plus weakest-link and Shapley attribution. Dispatches a team-coherence ZK proof asynchronously. Every agent whose reputation is private can be assessed only by a member of its governing org (403 `reputation_private` otherwise); a tombstoned agent returns 404.

## Request body

- object
  - `agent_ids` string[]: Explicit agent roster; required if `team_id` is not provided.
  - `team_id` string: Resolve roster from this team id; required if `agent_ids` is not provided.
  - `source` 'api' | 'playground'
  - `context` object, required
    - `action_type` string, required
    - `amount` number
    - `use_case` string
    - `risk_tolerance` string
    - `team_task` string
    - `coordination_mode` string
    - `trigger` string
    - `governance_median` number, nullable
    - `conflict_edge_count` integer
    - `conscience_universal` boolean, nullable

## Response `200`

Team risk assessment.

- TeamRiskAssessment: Team risk assessment row (`tra-…`). Produced by `POST /risk/assess/team`. Three-pillar result (portfolio + coherence + concentration) with weakest-link and Shapley attribution per member.
  - `assessment_id` string
  - `team_id` string, nullable
  - `agent_count` integer
  - `team_risk_score` number
  - `team_risk_level` string
  - `team_coherence_score` number
  - `team_recommendation` string
  - `portfolio_risk` object
  - `coherence_risk` object
  - `concentration_risk` object
  - `weakest_link_risk` object
  - `individual_assessments` RiskAssessment[]
    - `assessment_id` string
    - `agent_id` string
    - `risk_score` number: 0–1000 integer (higher = riskier).
    - `risk_level` 'low' | 'moderate' | 'high' | 'critical'
    - `recommendation` 'proceed' | 'proceed_with_caveats' | 'require_approval' | 'block'
    - `confidence` 'insufficient' | 'low' | 'medium' | 'high'
    - `contributing_factors` object[]
    - `suggested_thresholds` object
    - `explanation` string
    - `proof_id` string, nullable
    - `proof_status` 'none' | 'pending' | 'completed' | 'failed'
    - `created_at` string, date-time
  - `outliers` unknown[]
    - unknown
  - `clusters` unknown[]
    - unknown
  - `value_divergences` unknown[]
    - unknown
  - `shapley_values` object
  - `synergy_type` string
  - `explanation` string
  - `proof_id` string, nullable
  - `proof_status` string
  - `created_at` string, date-time

## Other responses

- `400`: Bad request
- `401`: Authentication required
- `402`: Paid feature gate — the caller's plan doesn't include this operation's feature flag. Emitted by `requireFeature` / `requireEntitlement` in `src/org/rbac.ts`.
- `403`: Forbidden
- `404`: Resource not found
- `429`: Rate-limit exceeded. The global per-IP limiter (100 requests/minute, applied to every `/v1/*` route) rejected this request. Back off until the window resets — `Retry-After` carries the cooldown in seconds and `X-RateLimit-Reset` the absolute reset time.
- `500`: Server error — request was well-formed but the server failed to fulfill it. Typically a downstream dependency (DB / RPC / external API) returned an unexpected error.
- `503`: An upstream dependency is currently unavailable. The request was not processed; retry after the cooldown window.

---

[API](https://skmtc.dev/mnemom/apis/mnemom-api.md) · [All operations](https://skmtc.dev/mnemom/apis/mnemom-api/llms.txt) · [OpenAPI document](https://skmtc.dev/mnemom/apis/mnemom-api/revisions/274b7a6ea182?raw)