Everything required to evaluate and deploy NADIR.

Confirm cohort VIN list, RO feed owner, telematics export owner, legal shadow language.

Deliver adapter manifest draft and sample batch template.

Attendees

Maint · IT · Legal optional

Output

Data contract v1

Quarantine report reviewed jointly. Scoring enabled on clean subset.

Maintenance labels true positives vs nuisance. Policy tweaks if agreed.

Verify workflow demo. Digest cadence confirmed.

Pass, fail, or stop with written appendix. Commercial renewal conversation only after pass.

VIN (17 char), RO identifier, close timestamp (UTC preferred), procedure category, and shop identifier.

Optional but valuable: part numbers for glass, ADAS kit replacement flag, technician notes.

NADIR validates identity before joining — malformed VINs land in a quarantine report, not silent scoring.

Required

vin · ro_id · closed_at · procedure

Format

CSV · JSON · webhook

Cadence

Daily batch minimum

Weekly CSV from MSO export is enough for most $750 proofs.

Webhook on RO close tightens MTTFF-RE measurement when telematics latency is low.

Idempotency keys prevent duplicate events when shops retransmit files.

POST /v1/repair-events
Authorization: Bearer ${NADIR_TOKEN}
Content-Type: application/json

{
  "idempotency_key": "ro-88421-vin-1HGBH41JXMN109186",
  "vin": "1HGBH41JXMN109186",
  "ro_id": "RO-88421",
  "closed_at": "2026-07-15T18:42:00Z",
  "procedure": "windshield_replacement",
  "shop_id": "SAFELITE-DTW-014"
}

Local shop time without timezone — converts incorrectly across DST.

RO marked closed before vehicle actually leaves bay — starts MTTFF clock too early.

Fleet unit numbers instead of VIN — must map through a stable crosswalk table.

Prefer the feed with earliest accurate close timestamp; document precedence in kickoff notes.

Conflicts surface in a reconciliation CSV — not auto-merged without operator ack.

RO payloads retain operational fields only — no customer PII beyond VIN and shop IDs in default pilot tier.

Retention windows defined in order form; export/delete available on request.

When a vehicle leaves a glass or body shop, start a clock at repair order close.

MTTFF-RE measures hours until NADIR assigns CAUTION or CRITICAL in the post-repair observation window.

If most events flag within seven days, your maintenance team gets actionable lead time before silent misalignment becomes a safety conversation.

• Median MTTFF-RE ≤ 168 hours is the default pilot target.
• Pass rate ≥ 70% of in-cohort events is the companion statistic.
• Events without telemetry are excluded — never counted as passes.

Join repair_events.ro_closed_at to health_transitions where tier ∈ {CAUTION, CRITICAL}.

Delta = first_flag_at − ro_closed_at in UTC hours.

Appendix lists excluded VINs with reason: no_telemetry, invalid_vin, pre_existing_critical.

SELECT
  re.vin,
  re.ro_closed_at,
  MIN(ht.scored_at) AS first_flag_at,
  EXTRACT(EPOCH FROM (MIN(ht.scored_at) - re.ro_closed_at))/3600 AS mttff_hours
FROM repair_events re
JOIN health_transitions ht ON ht.vin = re.vin
  AND ht.scored_at >= re.ro_closed_at
  AND ht.tier IN ('CAUTION','CRITICAL')
GROUP BY 1,2

Each dot or bar is one repair event in the pilot cohort.

Color encodes pass (≤168h) vs fail. Gray marks excluded rows.

Median line is the primary SLA statistic; mean is shown but not contractual.

Primary stat

Median hours

Threshold

168h

Coverage

% with data

Cherry-picked VINs with perfect telematics while hard cases were dropped from cohort.

RO timestamps backfilled days after close — inflates MTTFF-RE artificially.

Treating missing data as NOMINAL instead of excluded.

NADIR readouts include an exclusion appendix specifically to prevent silent passes.

Define cohort size, date range, procedure types (glass, front-end, mirror), and telemetry coverage minimum.

State median and pass-rate thresholds explicitly. Define stop conditions if CAUTION noise exceeds agreed bounds.

Clarify that shadow mode continues regardless of pass — expansion is a commercial decision, not automatic actuation.