Home/Platform/SEO Agent That Delivers Changes as Pull Requests

More search traffic from changes you approve

Tin is an SEO agent that audits your site, researches keywords and delivers site changes as pull requests. We connect it to your repository and run the weekly SEO work, giving your engineers changes they can inspect and merge through GitHub.

Book a call

Run SEO from the site's repository
System
Tin's System view: scheduled and available workflows for a project

What is an SEO agent?

An SEO agent carries out search work using AI, from reading pages and researching keywords to preparing edits. There are different ways to put those edits on a site. An agent can write into the CMS, suggest copy in a chat for someone to paste, or deliver a pull request to the site's repository. Tin uses the pull-request route for site changes.

The useful comparison is whether the team can review and undo each change. CMS edits depend on the site's controls; chat suggestions are transferred by the person handling them. A pull request records the proposed change for the owner to inspect and merge. Tin provides the SEO jobs through MCP, so the coding agent already in your repository can call them as it works.

Unreviewed edits cost you time tracing what changed

An agent edits a title, redirect or page on the live site, and an engineer has to find out what changed afterwards.

  • Edits take time to trace. Someone has to inspect the affected pages to reconstruct the agent's work.
  • Wrong data sends work astray. We encountered browser tests counted as traffic and Search Console connected to the wrong domain.
  • Checks come after publication. The engineer's corrections concern pages already in front of potential buyers.

A proposed change can be checked before publication, while the current page remains on the site.

SEO changes wait in pull requests you merge

The report and keyword inventory sit beside the proposed page work. We can trace an edit back to the finding that called for it.

Read the site before changing it

Tin reads up to 100 public pages in an audit. It checks technical SEO and whether AI answers mention, cite or recommend the business, then saves its findings and evidence in project Files. The site is unchanged by the audit. We use the report to consider what needs work.

Read the evidence behind each finding
Files
Tin's Files view: the project's knowledge base, reports and drafts as plain files

Research searches with evidence attached

The research job starts from buyer searches and competitor keywords, with a bounded sample of live Google results. Search Console is optional and adds your site's own queries. The owner sets a ceiling for paid data. Each inventory entry keeps its evidence for us to read when choosing page opportunities.

Connect keyword choices to evidence
Files
Tin's Files view: the project's knowledge base, reports and drafts as plain files

Inspect site edits before the merge

We deliver site changes through a GitHub pull request for the owner to merge. An engineer can read the edits together, using the same review route as a code change. The proposed work has a record in the repository before it becomes part of the site buyers visit.

Keep recurring SEO jobs scheduled

Tin saves the inputs and schedule with each recurring job, and handles the timers and retries when it runs. The Week view shows the scheduled work in the project. We use those jobs for ongoing research and reporting, so the next run starts from a task already defined.

Follow the scheduled SEO work
Week view
A week of a growth system in Tin: research, writing, checks, paid ads, email, review and measurement, day by day

Trace research through project files

Findings, plans and drafts remain plain files with git history. The team can open an earlier report, read the keyword evidence and follow revisions to the page draft. That record keeps the reasoning available when another engineer picks up the site work or a later run needs earlier research.

Trace the research behind an edit
Files
Tin's Files view: the project's knowledge base, reports and drafts as plain files

Tin's workflows audit, research and refresh your pages

Audit public pages

Check technical SEO and AI visibility, with findings saved for the next job. View audit workflows

Find buyer searches

Research keyword opportunities around the product, market and people likely to buy. View keyword workflows

Refresh page content

Rework an existing page using the research already saved in the project. View page workflows

Request missing backlinks

Prepare requests where another site mentions the company without linking to it. View backlink workflows

  • Claude Code
  • Codex
  • Cursor
  • GitHub
  • Google Search Console

Connect the repo that serves your site first

A public URL is enough for the audit. When we move to site changes, the outward-facing marketing repository is the usual place to begin.

Start with the public site
System
Tin's System view: scheduled and available workflows for a project

Begin with an audit

Add Tin through the command below to run the audit from a coding agent; the browser opens the same project.

Open the audit project →

codex mcp add tin --url https://app.tin.computer/mcp
Begin with the outward-facing repo
Files
Tin's Files view: the project's knowledge base, reports and drafts as plain files

Connect the marketing site

The outward-facing repository keeps the initial work on the pages that explain and sell the product.

Have us run SEO

Our people set up the project and take on its recurring research, writing and changes to the site.

Each SEO workflow is open, editable code

Examine the audit steps

Read a job's folder to inspect the instructions, inputs and evaluations used for its output.

Run SEO locally

Tin can use your team's keys and data in an installation on its own machine.

Adjust a research job

The workflow file can be edited to change the task called by the coding agent.

Check the code license

Open source, Apache 2.0.

Talk to Tin

Let's discuss the SEO work we could run from your site's repository. We handle setup, the weekly jobs and the choices behind proposed edits; the code stays with your team.

Book a call

FAQ

Does it work if our site runs on a CMS?

The audit works on a public site without a GitHub connection. It reads the pages and saves the findings in the project. The site-change route described here uses GitHub, so we would discuss your publishing setup before choosing how to carry the findings into changes on a CMS site.

How many pages does the audit check?

Each audit checks up to 100 public pages. It is sized for a startup or product site, and covers technical SEO plus whether AI answers mention, cite or recommend the business. The resulting report includes the evidence behind its findings, so the next task can start from a specific page problem.

Is there a limit on paid keyword data?

Paid data is fetched during the job under a cost ceiling you set. That applies to keyword and search-result research; Search Console can also supply your site's queries when connected. The job saves the inventory and its evidence, which we use when choosing searches worth addressing with a page.

How is this different from asking Claude Code to do the SEO?

Claude Code can run Tin through MCP, so the two work together. Tin supplies the SEO job, its live data, schedule and project memory. That leaves a record the agent can read on a later run. We set up and run the work around that record for your site.

Talk about your site's next SEO work

Talk with the founders and engineers who set up the SEO jobs and run them. We can discuss which audit findings deserve attention first and how proposed site changes would reach your engineers through GitHub.

Book a call