TinTinWorkflows
GitHubSign in

Get taught where students first pick their tools

A student who learns a tool in class often keeps it. Tin finds public courses that teach the job your product does, ranks them by when the instructor next chooses tools, and drafts a teaching kit plus one note per course in your voice.

Try in browser →
codex mcp add tin --url https://app.tin.computer/mcp
Course placement
outreach.syllabus_placement
outputreports/outreach/syllabus/{run_id}.md
guardrailNothing is sent. You decide which instructors to write to.
needsA product students could learn on. A feature map and growth plan help it describe the job.
required inputsnone
optional inputsteaching_job, alternatives, subjects, geography, education_offer, max_courses

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. 01Works out what a student would use your product to do, from the feature map or your own words.
  2. 02Searches public course pages and syllabi in the subjects and regions you choose.
  3. 03Ranks the courses by fit and by when the instructor next picks tools, skipping courses earlier runs listed.
  4. 04Drafts a teaching kit and one note per course.
ask your agent

Find university courses that teach field survey data collection, and draft a teaching kit for instructors.

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

A teaching kit needs a lesson that works on the first try. Your agent knows the product well enough to write one.

All workflows →

Questions.

What should I offer instructors?

Whatever you can sustain: free seats, a class plan, setup help. Leave it empty if you have not decided, and the kit says so.

Does it email the instructors?

No. It drafts the notes. Sending them is up to 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.

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

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