Working with AEO/GEO. Measuring company visibility in LLM responses

Shows how often LLMs name your company and your competitors

You will learn how to use a coding agent to build a service that measures a company's visibility in LLM responses—how often models mention you and your competitors when someone asks them for advice on choosing a product. We will work through this using the note-taking service Granola and four of its competitors.

By the end, the service will be able to:

  • Ask models sets of questions on behalf of different buyer personas
  • Call several LLMs in two modes—with web search and without it
  • Parse the model responses
  • Turn the results into visibility metrics
  • Collect data on a schedule within a budget you set

You can point it at your own company and competitors from the start—then you will get a working tool rather than a training example.
 

By the end of this case you'll have a working product and a set of reusable skills:

designing the measurement: question sets, buyer personas, the set of LLMs and the call modes parsing model responses: mentions, sentiment, position
visibility metrics: mention rate, first mention rate, sentiment split
storing and collecting data on a schedule: scheduling, change log, budget and error control

How do I get access to the program?

This case is part of the GoPractice “Build with AI” subscription. You can start right now.

Learn more