An AI visibility audit you can read, rerun and fork
Tin writes five buyer questions that never name your product, asks them, and measures whether the answers find and recommend you. The result is published to your project as AI_VISIBILITY.md.
codex mcp add tin --url https://app.tin.computer/mcpWhat the workflow does
A Tin workflow is a repeatable job: declared inputs, a bounded run and a defined output. The steps below are what this one does, every time.
- 01Takes the target you name: a product, site or brand.
- 02Writes five target-blind buyer questions, the way a real buyer would ask.
- 03Records whether the answers mention, cite or recommend the target.
- 04Publishes AI_VISIBILITY.md, which the answer page workflow builds on.
Run Tin's AI visibility audit for our product and tell me which buyer questions we are missing from.
What every workflow here comes with
Battle tested on real products
These are the workflows we run for real companies. Claw Messenger went from about $45 to $2,105 in monthly revenue in 124 days on them. Each one has declared inputs, bounded execution and tests, and anything public waits for your review.
See the case study →Open source: read it, fork it, self-host it
Apache 2.0. Every workflow is a folder in the repository: the steps it runs, the data it reads and what it is allowed to do. Change it, or run the whole system on your own machine.
Open the repo →Runs on the agent that already knows your product
Your agent knows what category you compete in and who you lose to, so the target and the follow-up are specific.
All workflows →Using something else for this today?
What this workflow replaces in each product, and what it does not.
Workflows that run well with this one
Questions
Is this a daily tracking dashboard?
No. It is an audit you run on demand or on a schedule, with the method in the open. Dashboards that track many prompts across many engines every day are a different product.
Why are the questions target-blind?
If the question names you, the answer will too. Blind questions show whether a buyer would ever hear about you.
Is Tin really open source?
Yes. Tin is licensed under Apache 2.0 and the source is at github.com/tin-computer/tin. You can read every workflow, change it, and self-host the whole system.
Which coding agents can run Tin workflows?
Any agent that speaks MCP, including Claude Code, Codex and Cursor. There is also an API, and the same projects run in the browser at app.tin.computer.
Why run marketing from a coding agent?
Because it already knows your product. It has the repository open, so it fills workflow inputs accurately, reviews output against what the product really does, and can act on the results in the same session.