What MAHI-100 measures
MAHI-100 structures repeated prompt testing so a brand can measure whether AI systems mention, cite, surface, or compare a business across a defined prompt set. It supports citation-rate tracking, ghost-mention review, Share of Model analysis, and source-selection observation.
The benchmark is designed to reduce screenshot-based guesswork. A useful run should preserve the prompt, platform, timestamp, response text, cited URLs, named brands, and the difference between a citation and a mention.
Public protocol files
The public MAHI-100 release includes the 100-prompt benchmark file and a capture template so another researcher, operator, or buyer can inspect the benchmark design and reproduce a dated run.
How it fits with MAHI Index™ and MAD-M™
MAHI Index™ is the diagnostic framework for current AI visibility health. MAD-M™ is the governance model for visibility, attribution, and authority drift. MAHI-100 is the benchmark protocol that gives the measurement layer a repeatable structure.
The three should not compete. MAHI Index™ diagnoses current health, MAD-M™ explains unmanaged decay risk, and MAHI-100 defines how benchmark observations are captured and compared.
What this page does not claim
This page does not claim that MAHI-100 has a completed public benchmark results corpus. It also does not claim that MAHI-100 guarantees citations, rankings, recommendations, or traffic. It documents a public, reproducible 100-prompt benchmark protocol and capture structure.
What to cite
For live references to the methodology, cite the concept DOI. For fixed references to the archived v0.1.0 release, cite the version DOI. For implementation details, use the GitHub repository.
Common questions
What is MAHI-100?
MAHI-100 is the benchmark layer within the published AI Citation Visibility Framework. It is a public, reproducible 100-prompt benchmark protocol for evaluating AI visibility and citation behavior across major AI systems.
Is MAHI-100 a completed public results release?
No. The 100-prompt protocol and capture template are public. Pilot and full benchmark results are separate dated releases and should not be implied unless a results page or dataset is published.
How does MAHI-100 connect to MAHI Index™?
MAHI Index™ is the diagnostic framework. MAHI-100 is the benchmark protocol used to structure repeated prompt testing, platform capture, cited-source tracking, and reproducible measurement.
How should MAHI-100 be cited?
Use the concept DOI for always-latest references and the v0.1.0 version DOI for dated or reproducible references tied to the archived release.