Research hub

AirPulse AI-Search Measurement Research

This is the canonical index for AirPulse measurement research. Use it to find the current stability study, the permanent calculation methodology, the prompt-selection methodology, public aggregate downloads and the update record. Individual pages link back here so readers do not have to reconstruct the evidence across unrelated posts.

Maintained by the AirPulse research and data teamPublished July 20, 2026Updated August 10, 2026

Why AI-search measurement needs repeated observations

An AI answer is generated fresh each time, not retrieved from a fixed ranked list. The same prompt on the same engine can name a brand today and omit it tomorrow. A single screenshot is therefore evidence of one answer, not an estimate of visibility. AirPulse research measures each prompt-engine pair as a repeated series over time and reports the resulting rates with their uncertainty.

Current research finding

AirPulse's frozen 30-day study covered 30,504 production responses. Mention status changed between consecutive observations 9.7% of the time. 35.9% of sufficiently repeated prompt-engine cells changed state at least once. Consecutive cited-domain sets had 0.396 mean Jaccard overlap.

A separate rolling validation extracted on July 20, 2026 covered 30,146 responses and found a 10.0% consecutive mention flip rate, 33.9% mixed-state cells and 0.390 mean source overlap. The validation is reported separately so the original study does not become a moving target: the frozen cohort keeps its published numbers, and the rolling window checks whether the pattern still holds.

Diagram showing one prompt and one engine measured repeatedly across time. — The measurement unit behind every AirPulse research number: one prompt × one engine, observed repeatedly over time.

Research library

Six pages, six jobs. Start with the study if you are questioning a one-run result, the methodology if you are defining how your team measures, the prompt-selection page if you are deciding what to measure, the trial protocol if you are testing whether a change worked, the crawler reference if you are reading server logs and being asked whether a bot hit means an AI cited you, and the citation-stability result if you have a first citation and want to know whether it lasts.

Original study · Start here

How Many Times Should You Run an AI Search Prompt? Evidence From 30,504 Responses

Use it when: You are deciding whether a one-run visibility result is trustworthy, or how many repeated runs to schedule.

Methodology

AirPulse AI-Search Visibility Measurement Methodology

Use it when: You need the permanent definitions, calculations and reporting contract your team should follow.

Prompt-selection methodology

Which AI Search Prompts Should Your Brand Track?

Use it when: You are building or revising the prompt roster that the measurement methodology takes as its input.

Research protocol

How to Prove a GEO Change Improved AI Visibility

Use it when: You are about to publish or change a page and need defensible evidence of whether it moved AI visibility.

Crawler reference

Which AI Crawlers Visit Your Website — and What Are They Doing?

Use it when: You are reading server logs, setting robots.txt by crawler purpose, or being asked whether a crawler hit means an AI cited you.

Research result

How Stable Is a New AI Citation? Evidence From the First 16 Perplexity Observations

Use it when: You have a first AI citation and need to know whether it is repeatable presence or a one-off answer.

The frozen citation-stability cohort, one row per valid observation: cited flag, citation-list position and exposed citation count. No raw answers or tenant data.

Download →

Core definitions

Term	Definition
Prompt-engine cell	One exact prompt paired with one fixed answer engine
Valid run	One timestamped execution that returned a usable answer under the declared failure rules
Mention rate	Valid runs naming the brand divided by valid runs in the same scope
Own-domain citation rate	Valid runs citing the brand's registrable domain divided by valid runs
Source coverage	Distinct valid cited URLs or domains observed across repeated runs
Jaccard similarity	Intersection divided by union for two comparable source sets

The full definitions, calculations, uncertainty rules and known limitations are maintained in the measurement methodology. Every study on this hub is an observational production cohort, not a random sample of all brands or prompts, and none of it estimates the causal effect of a single content change. The study page lists what its findings do and do not support. To test one declared page change against a frozen baseline and matched controls, follow the first-citation trial protocol.

How the research connects to AirPulse

Prompt Visibility applies repeated measurement to prompt-engine cells.
Citation Visibility separates own-domain, third-party and source-history outcomes.
Prompt Analysis helps teams group and maintain the prompt roster.
AI Visibility provides the broader product context.
AI Traffic measures downstream referral sessions separately from answer visibility, and separates verified crawler roles from human referrals.
The free GEO Audit is the diagnostic entry point; the crawler reference explains why crawler access alone is not measured visibility.

The research pages explain the measurement rules. Product pages explain the workflow. Neither should substitute for the other.

Update record

Date	Change
July 13, 2026	Frozen production study and corrected evidence strategy established
July 20, 2026	Rolling validation added; first research cluster prepared for publication
July 27, 2026	First-citation trial protocol and preregistration worksheet added to the library
August 3, 2026	Crawler reference and audit worksheet added, after the protocol page's first observed citation on August 1

Future updates will list material changes to the cohort, parser, prompt roster, source normalisation or conclusions. Silent rewrites should not alter a published headline number. New studies will be added to the research library above as they are frozen and reviewed.

How this page was made

AirPulse analysed aggregate records from its production read replica in a read-only transaction. The public study excludes customer names, tenant identifiers, raw prompts and raw answers. The analysis code groups observations by brand, prompt and engine, orders them by time, and compares consecutive valid runs. Harsh Songra drafted the page; the AirPulse research and data team reviewed the claims and the downloadable aggregates before publication. AI assisted with structure and editing, but the published numbers must reproduce from the frozen evidence file.

Primary references

See the measurement running on your brand.

The free GEO audit runs your buyers' real questions against four engines. The research above explains how to read what comes back.

Book a demo Run free GEO audit