Audit onboarding mentorship evidence integrity

What it's for

Makes Gitrevio's onboarding and mentoring claims auditable: leadership sees whether the cohort, source and milestone evidence is trustworthy before comparing ramp outcomes.

What you give it

Inputs split into evidence read from your connected systems, calibration your team owns, and numerical controls that affect precision but never the result's meaning.

{
  "as_of_ms": 864000000,
  "evidence_cutoff_ms": 864000000,
  "mentorship_relationships": [
    {
      "consent_verified": true,
      "corroborated": true,
      "ended_at_ms": 518400000,
      "episode_id": "onboarding-0",
      "evidence_verified": true,
      "id": "mentorship-0",
      "mentor_ref": "mentor-0",
      "recorded_at_ms": 172800000,
      "source_id": "mentorship",
      "started_at_ms": 86400000
    },
    {
      "consent_verified": true,
      "corroborated": true,
      "ended_at_ms": 518400000,
      "episode_id": "onboarding-1",
      "evidence_verified": true,
      "id": "mentorship-1",
      "mentor_ref": "mentor-1",
      "recorded_at_ms": 172800000,
      "source_id": "mentorship",
      "started_at_ms": 86400000
    },
    {
      "consent_verified": true,
      "corroborated": true,
      "ended_at_ms": 518400000,
      "episode_id": "onboarding-2",
      "evidence_verified": true,
      "id": "mentorship-2",
      "mentor_ref": "mentor-0",
      "recorded_at_ms": 172800000,
      "source_id": "mentorship",
      "started_at_ms": 86400000
    },
    {
      "consent_verified": true,
      "corroborated": true,
      "ended_at_ms": 518400000,

What you get back

This is the actual output of running the example above — computed by the same function the platform calls, not an illustration.

{
  "cohort_summaries": [
    {
      "autonomy_observed_fraction": 1,
      "cohort_id": "2026-q2",
      "episode_count": 6,
      "median_observed_autonomy_days": 4,
      "mentorship_coverage": 1,
      "role_id": "backend",
      "team_id": "payments"
    }
  ],
  "coverage": {
    "identity_coverage": 1,
    "milestone_coverage": 1,
    "source_coverage": 1
  },
  "decision": "accepted",
  "finding": "evidence_ready",
  "gates": {
    "integrity_passed": true,
    "maximum_autonomy_days": 120,
    "minimum_cohort_size": 5,
    "minimum_identity_coverage": 0.95,
    "minimum_milestone_coverage": 0.8,
    "minimum_source_coverage": 0.9
  },
  "integrity_diagnostics": {
    "duplicate_snapshot_expected_episode": 0,
    "duplicate_snapshot_source": 0,
    "source_expected_episode_missing": 0
  },
  "interpretation": "Milestones and mentorship are cohort-system evidence, not employee ratings. Small groups are suppressed; commit volume is never treated as autonomy, and this audit cannot support hiring, firing, compensation, or mentor ranking.",
  "method": "point_in_time_onboarding_milestone_mentorship_lineage_audit_v1",
  "repair_queue": [],
  "summary": {
    "autonomy_observed_count": 6,
    "episode_count": 6,
    "episode_with_milestone_count": 6,
    "median_observed_autonomy_days": 4,
    "mentored_episode_count": 6,
    "suppressed_small_group_count": 0
  }
}

How it works

Statistical audit & measurement — Check whether a number is fit to decide on: coverage, timing, reconciliation, and the gaps a dashboard hides.

1. 1 Freeze the tenant, cohort window, evidence cutoff, consent, identity resolution, source snapshots and milestone-definition version; reject future, orphan, duplicate, impossible or unverified records.
2. 2 Reconcile each onboarding episode to complete HR, Git and mentorship snapshots, enforce milestone time order from first change through independent delivery to autonomy, and require every mentor relationship to be consented and corroborated.
3. 3 Publish only cohort/role/team aggregates above the privacy threshold, keeping lineage defects separate from slow observed autonomy and suppressing small groups rather than exposing people.

Before you trust it

Every tool in the catalog ships with the conditions under which its answer is meaningful — and the conditions under which it should abstain instead of guessing.

Calibrating it to your org

Calibration workflow

1. 1 Define the management decision, target outcome, aggregate unit, privacy boundary, cadence, and prediction/intervention horizon for this organization.
2. 2 Build a tenant-scoped historical cohort using only information available before each prediction or decision; preserve zero periods, censoring, assignment probabilities, and unresolved outcomes when the method requires them.
3. 3 Estimate statistical parameters on training history, but obtain costs, utilities, risk tolerance, practical-effect thresholds, capacity, and policy constraints from accountable decision owners.
4. 4 Validate on later time windows or held-out aggregate units at the deployment grain, against a simple baseline and the function-specific validation strategy.
5. 5 Deploy only if the returned decision clears evidence, overlap, calibration, robustness, and guardrail checks; warning, unsupported, schema-gap, and fallback decisions are abstentions.
6. 6 Monitor realized outcomes, data drift, coverage, and decision regret; recalibrate at a governed cadence or after a detected regime/definition change, never merely because a stakeholder dislikes the result.

Call it from your AI

You don't wire up 388 tools in your MCP client. The GitRevio MCP server exposes 18 tools, three of which let an agent search the catalog, read a tool's schema, and run it — so the assistant finds this one on its own.

gitrevio_capabilities_search
  { "q": "audit pointintime onboarding cohorts ordered autonomy" }
  → finds "audit_onboarding_mentorship_evidence_integrity"

gitrevio_capability_describe
  { "capability_id": "audit_onboarding_mentorship_evidence_integrity" }
  → returns the input schema and agent guidance shown on this page

gitrevio_capability_run
  { "capability_id": "audit_onboarding_mentorship_evidence_integrity", "arguments": { ... } }
  → returns the result shown above

Works in Claude Desktop, Claude Code, Cursor, Cline, Continue.dev, Goose and Aider. See the MCP server.

Related tools

See every tool in People, retention & knowledge →