Cheap Seats
Menu

Open-source, self-hosted AI visibility tracker

Do AI assistants recommend you?

Ask your buyers' questions. See where your brand stands. Know which pages to fix first.

Get started Explore the demo

Free on your Claude subscription; ChatGPT optional. Your prompts stay in your own git repo.

Example snapshotCheap Seats

Prompt set

Head-to-heads

Does AI choose Cheap Seats when buyers compare?

Recommended
14%
Named
100%

Example results · Search track · October 22, 2026

Inspect the real dashboard

From buyer questions to better answers

  1. Ask real questions

    Run the prompts your buyers use, across search and recall.

  2. See where you stand

    Separate recommendations from mentions, with the evidence behind each answer.

  3. Fix what matters

    Work through ranked page improvements and track the results.

Inside each run

  1. Your buyers' questions

    Prompt sets are TOML files in a config repo you own, one per category of buyer question, written the way someone who has never heard of you would type them. Changes go through pull requests.

  2. Two tracks, every assistant

    Each configured assistant answers every prompt on search, where it must search the web first, and recall, with no tools. You see both what the web says today and what the model already believes.

  3. Graded answers

    A second Claude call grades each answer recommended, mentioned or absent, with your position, the top pick, every product named, the objections raised, and why you weren't #1.

  4. Share of voice and rankings

    Each run shows rates per assistant and track with 95% intervals, and share of voice. Rankings follow your place day by day, and carry on through reworded, added and removed prompts.

  5. A ranked fix list

    Each run ends with Fix these first: the exact page to create or change, what it must say, the prompts it would flip, an effort estimate, and which of your sites it belongs on, with its owner.

Start here, move on when you're ready

I built Cheap Seats to make my own product better. It draws on a lot of tools, Gauge first among them, along with Profound, Peec AI and others. They do a lot, and most of it I didn't need; what I did have was Claude and ChatGPT subscriptions with tokens to spare. So Cheap Seats does the part you'll use most: ask your buyers' questions, grade the answers, show which pages shape them, and say what to fix first. It runs on those subscriptions, on your own machine, with nothing to buy. It's free, and it always will be.

It's for the people who own how a product is described: product marketing, docs, the blog and the website, and anyone starting to measure AI visibility. I hope you find it useful. If you grow out of it, because you need engines it doesn't ask, a hosted service, or reporting for many clients, do whatever suits you. I'd suggest Gauge; that team is great. The buyer questions you've refined are plain text in your own repo, ready to take with you. How the tools compare.

Open source, on your own infrastructure

Get started

A fresh checkout runs against an example config that measures Cheap Seats itself. You need Go and Claude: the claude CLI logged in to a Claude subscription (no API key, no spend), or an Anthropic API key. ChatGPT is optional: the codex CLI or an OpenAI key adds its answers.

CHEAPSEATS_CONFIG=examples/cheapseats-config/cheapseats.subscriptions.toml go run ./cmd/cheapseats serve
# then open http://127.0.0.1:3000

Read Getting started, then start your own config repo from the template.