A calibrated, reproducible measurement protocol. No SEO games, no rewriting, no marketing math — every step is auditable.
Everything PartSentinel produces maps to this framework. Pillars set the score weighting. Metrics are the units of measurement. Deliverables are what the client receives.
Reality Gap — divergence between AI output and catalogue truth.
Inference Risk — sensitivity of what AI can reconstruct. Key differentiator.
Competitive Visibility — Share of Answer + Category Authority.
Diagnostic on 50–100 SKUs. Mode 1 (Blind) or Mode 2 (Full).
Extension across families, markets, languages, competitors.
Continuous monitoring + remediation + Negative Knowledge Layer.
Brand monitoring tells you what people say about your company. PartSentinel measures what AI says about each individual SKU, OE number, or technical reference in your catalogue.
We query 8–12 large language models in parallel with deterministic seeds, fixed temperatures, and rate-limited concurrency. The same audit run twice produces the same result within 1 score point.
Aftermarket, electrotechnical, aerospace, chemicals — each vertical has its own prompt template, scoring weights, and ground-truth schema. No one-size-fits-all.
We never invent the right answer. The reference truth is your BMEcat / ETIM / PIM / product reference data. We measure deviation, not opinion.
Every Sentinel Score is reconstructible from the raw model responses, the calibration set, and the scoring formula — all of which we publish.
From your catalogue to a regulator-ready dossier.
BMEcat, ETIM, CSV, JSON, or PIM API (SAP, Inriver, Akeneo, Pimcore). Native parsing — no manual mapping for standard formats.
We stratify references by vertical, age, OE coverage, and revenue contribution. Default audit: 50–500 references; full-catalogue: every reference.
Each reference is queried against 8–12 LLMs with calibrated, vertical-specific prompts. Per-reference: ~32 prompts × N models.
Free-form responses are parsed into a structured schema (identifier, application, cross-references, specs, procedural depth) using a deterministic extractor.
Extracted facts are aligned to your authoritative data. Each fact is labeled accurate / partial / hallucinated / leaked / obsolete.
We compute the Sentinel Score (0–100) for each reference and roll it up by vertical, brand, model, and time.
Excel raw export, executive PDF, drilldown dashboard, and AI Act dossier (Article 53(1)(d) compliant) — all under signed checksums.
Refreshed quarterly. Last refresh: 2026-04-22.
Each prompt is calibrated to elicit a single, schema-conformant fact. Free-form prose is rejected. Examples are versioned and published.
# Vertical: automotive_aftermarket
# Schema: identifier_v3
You are answering a single question about an automotive aftermarket
reference. Reply ONLY with the JSON schema below — no prose.
REFERENCE: "{{ref_code}}"
{
"identifier_confidence": 0.0–1.0,
"applications": ["{vehicle make/model/year}"],
"cross_references": ["{competing OE/IAM codes}"],
"specs": { "{spec_name}": "{value}" },
"source_hints": ["{public_url_or_null}"]
}The Sentinel Score is a calibrated, weighted aggregate. Each dimension is scored on 0–100. Per-vertical weights and leak-penalty constants are disclosed inside the signed audit dossier under NDA.
Does the model know the reference exists and what it is?
Does it correctly map to OE / IAM / competing codes?
Does it correctly state where the part fits (vehicle, machine, system)?
Does it know the technical specifications, not just the marketing copy?
Is the information current — or stuck on a 2019 catalogue?
We never declare a model wrong without your authoritative data. Three sources are accepted:
Every audit run produces an immutable manifest: prompt versions, model versions, calibration constants, and seed values. Reproducibility is the contract.
Yes. We support an on-premise mode where the audit pipeline runs inside your VPC and only the aggregated scorecard leaves the perimeter.
Quarterly is the default. Verticals with rapid catalogue rotation (electrotechnical, automotive aftermarket) benefit from monthly delta audits.
We never publish or train on customer data. Leaks are only ever flagged to the customer, never disclosed externally.
Coverage of the LLMs your customers actually use. Panel is updated quarterly to follow market share, with prior-quarter overlap for trend continuity.
Run this methodology on 1 of your references — free, 90 seconds, 6 / 342 models live, no account required.