Docs

Cheap Seats asks AI assistants the questions your buyers ask, grades whether each answer recommends you, and builds a ranked list of fixes. These pages cover running it, configuring it for your brand, reading what it finds, and deploying it.

1. Getting started
   Run Cheap Seats on your own machine at no cost, on the Claude subscription you already have, then point it at your own brand.
2. Configuration
   cheapseats.toml, the file that says whose brand Cheap Seats measures, with which assistants, and how much it may spend.
3. Cost and budget
   What Cheap Seats costs to run every day, what a real run cost, and how the daily budget cap keeps model spend under control.
4. Prompt sets
   The buyer questions Cheap Seats asks, as TOML files in your config repo, with ids that keep their history.
5. Reviewing your prompts
   A monthly review of the prompts themselves, from the answers you already have — which tell you nothing, which move for no reason, which are answered about something else, which ask the same thing twice, and what no prompt asks. Free.
6. Reading results
   Verdicts, tracks, the run page's rates, share of voice, sources and sentiment, what the assistants searched, rankings, fix lists and quick wins.
7. Which AI engines Cheap Seats asks, and why
   Cheap Seats asks Claude and OpenAI models through their APIs and CLIs, not scraped consumer apps. Why, what that misses, and how other tools reach Google AI Overviews, Perplexity and more.
8. How grading works
   How Cheap Seats decides whether an AI assistant recommended a brand, mentioned it or left it out, which assistants it asks, and how to check every grade.
9. Metric definitions
   Every number Cheap Seats reports, with its formula and denominator, and how each maps to Peec AI, Profound, Gauge, Otterly.AI, Ahrefs, SE Ranking, Elmo and Limelit Open.
10. How big a change Cheap Seats can detect
    Why AI answers vary from run to run, the intervals and tests Cheap Seats uses so a fluke doesn't read as a trend, a worked example of how many points a run and a week can resolve, and when more samples help.
11. From fix to pull request
    How a quick win becomes a pull request with Claude Code, shown on cheapseats.dev's own fix list.
12. Free site checks: audit, citations, AI crawlers
    Three checks that call no model and cost nothing, the site audit of what AI crawlers can read, the citation check of which cited pages name you, and AI crawler counts from your access logs.
13. Self-hosted AI visibility tracker: Docker and Kubernetes
    Run Cheap Seats, the open-source AI visibility tracker, in Docker, on your own Kubernetes cluster with the Helm chart, or on an exe.dev VM. One container, one SQLite file, and your prompts go only to the model providers you configure.
14. Re-grading stored answers
    Grade the answers older runs already have again, under today's grader, brand and competitors, so a grading change carries the trend on instead of restarting it.
15. Sharing a run
    A read-only, expiring, revocable link to one run's report for someone without a sign-in, what it shows and leaves out, and how the token is kept safe.
16. Deploying
    Docker, Kubernetes with the Helm chart, or an exe.dev VM.
17. Upgrading
    Cheap Seats keeps your history across upgrades.
18. CLI, API and MCP
    Every command, JSON route and MCP tool, and how access works.