TinTinWorkflows
GitHubSign in

Pages already name you. Ask them for the link.

Some pages, including sources AI answers cite, already name your product but do not link to your site. Each week Tin finds new ones and drafts one short ask per page in your voice, so you can request the link yourself.

Try in browser →
codex mcp add tin --url https://app.tin.computer/mcp
Unlinked mentions to backlinks
organic.mention_backlinks
outputreports/backlink-asks/{run_id}.md
guardrailIt never sends, posts or contacts anyone. A hard no on cold email in your plan withholds the drafts.
needsA product with a public name. The onboarding plan and an organic audit help it fill in the rest.
required inputsnone
optional inputsbrand_name, domain, aliases, max_mentions, recency_days
sourcegithub.com/tin-computer/tin →

What the workflow does.The same steps, every run.

A Tin workflow is a repeatable job: declared inputs, a bounded run and a defined output.

  1. 01Uses the name, domain and aliases Tin already holds, plus any you add, such as a former name or a common misspelling.
  2. 02Finds pages and AI-cited sources that mention the product without linking to your site.
  3. 03Investigates each new page and drafts one short ask in your voice.
  4. 04Keeps a ledger, so it never repeats an ask from an earlier week.
ask your agent

Each week, have Tin find pages that mention us without linking to our site and draft the asks.

What every workflowcomes 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 the old product names and the founder's name, which is where many forgotten mentions hide.

All workflows →

Using something else for this?What it replaces, and what it does not.

Ahrefs alternativeSEOSemrush alternativeSEO

Runs well with.Workflows that feed this one, or follow it.

SEO and AI visibility auditorganic.auditAI visibility auditvisibility.auditWriting style capturestyle.capture

Questions.

Will it email site owners for me?

No. It drafts the asks. You decide which to send and send them yourself.

Why AI-cited sources?

Pages that AI answers cite carry weight in those answers. A link from one of them helps both search and AI visibility.

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.

Add Tin to your coding agent.It takes one command.

Try in browser →
codex mcp add tin --url https://app.tin.computer/mcp