Methodology v2.4

A score is only as good asthe math behind it.

Every Pulse Labs metric is reproducible, versioned and traceable to raw model responses. Here is exactly how we measure what AI thinks about your brand.

STEP 01

Prompt battery design

Each scan dispatches a structured battery of prompts spanning neutral discovery, comparison, recommendation and adversarial framings — across brand themes and audience personas. Prompts are versioned so scores stay comparable over time.

STEP 02

Multi-model dispatch

Prompts run in parallel against the major generative engines — GPT-5, Claude Sonnet 4.6, Gemini 3 and more — with identical phrasing and zero brand priming. Web-grounded variants capture how models behave with live retrieval.

STEP 03

Forensic scoring

Every raw response is scored for sentiment, brand visibility, framing, competitor substitution and factual accuracy. Claims are audited against verifiable sources to flag hallucinations, and red flags are cross-corroborated across models.

STEP 04

Consensus & NCI computation

Per-model scores roll up into a cross-model consensus matrix with divergence weighting. The Narrative Consensus Index (NCI) combines sentiment, visibility and narrative control into one benchmarkable 0–100 figure.

Score definitions

What every number means

Sentiment0–100

How favorably models describe the brand, weighted by framing strength and the prominence of positive vs. negative claims.

Visibility0–100

How often the brand appears unprompted in category, comparison and recommendation queries — the AI equivalent of share of shelf.

Narrative Control0–100

How closely the model's framing matches the brand's intended narrative themes, vs. competitor or third-party framing.

Divergence0–100

How much models disagree with each other. High divergence means your AI reputation is unstable across engines.

NCI0–100

The Narrative Consensus Index — the composite headline score combining the dimensions above with divergence weighting.

Integrity principles

The rules we never break

Immutable records

Scan results are write-once. Scores are never retroactively edited — methodology changes only apply forward.

Full provenance

Every score links back to the raw model responses that produced it. Nothing is a black box.

No brand priming

Prompts never hint at a desired answer. We measure what models actually say, not what brands hope they say.

Versioned methodology

Scoring logic carries a version tag on every record, so longitudinal comparisons are always apples-to-apples.

Honest limitations

LLM outputs are stochastic. We report consensus across repeated, multi-model sampling — never a single response.

Methodology changelog

Versioned, so your trends stay honest

  1. v2.4Jun 2026

    Added truth-audit hallucination forensics, counterfactual crisis simulation and theme-ownership displacement analysis to the scan pipeline.

  2. v2.3Apr 2026

    Introduced persona-resonance profiling and per-model cognitive lens analysis. Expanded model coverage to 8 engines.

  3. v2.2Feb 2026

    NCI composite formula refined with divergence weighting. Theme intelligence expanded to 5-theme batteries.

  4. v2.0Nov 2025

    Cross-model consensus matrix and immutable scan provenance chains introduced.

Want the full technical methodology paper?

We share the complete scoring specification, prompt battery structure and validation studies with prospective enterprise customers.