Skip to content

Friday SEO run capped at three actions

Every Friday it reads a playbook file, pulls last week's search and revenue numbers, and picks at most three actions for the week instead of a long report. It updates the playbook with what it learned, and page changes stay behind your approval.

MarketingWorks with Claude Code · Claude Desktop with MCP+1Community example
Build your promptSee requirements

What it does

  • Reads the SEO playbook file at the start of each run
  • Pulls last week's search clicks and organic revenue
  • Picks at most three actions for the week
  • Drafts the page or content change for each action
  • Rewrites the playbook with what it learned

Your approval boundaries

Approval required

These actions always wait for your yes:

  • Publishing any page change
  • Changing any setting in the search console

You decide what happens next.

More about this workflow

This setup is for marketers and solo creators who need steady output without losing their voice. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it reads the SEO playbook file at the start of each run. Next, it pulls last week's search clicks and organic revenue. Then it picks at most three actions for the week. After that, it drafts the page or content change for each action. Finally, it rewrites the playbook with what it learned. It works with your analytics, docs and docs site, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before publishing any page change and changing any setting in the search console, and says plainly if a step cannot be undone.

“So now it picks 3 actions a week, max.”
Noah Kagan @noahkagan · Nov 4, 2026
Before you startAnalytics · Docs accessScoped permissionsClaude Code or Claude Desktop with MCP
Explore required tools and model recommendations

Tools and access

  • Google Analytics

    Handles the analytics part of this job. Grant Viewer role.

    API required: Yes. Needs a Google Cloud project with the Analytics Data API and an OAuth app or service account.

    Sign up: Google Analytics

  • Google Docs

    Handles the docs part of this job. Grant one folder, create and edit only.

    API required: Yes. Needs a Google Cloud OAuth app with the Docs API turned on.

    Sign up: Google Workspace

  • Docs site

    Handles the docs site part of this job. Grant draft or branch access, not publish.

    API required: Optional. Your docs repo or CMS. Most agents work through a branch or draft.

    No sign-up needed

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

GPT-6.1 Sol

Strong general writer at a mid price.

$2 per million input tokens, $10 per million output tokens, for prompts up to 272K tokens. Longer prompts cost $4 in and $15 out.

OpenAI docs as of October 11, 2026

Cheaper backup

GPT-6 Luna

Very low cost for first drafts and digests.

$0.10 per million input tokens, $0.50 per million output tokens, for prompts up to 272K tokens.

OpenAI docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

your rules and past learnings

e.g. 3

2Your prompt

4 of 4 still empty
Fill these in before you run it: [SITE AND SEARCH CONSOLE PROPERTY] [PLAYBOOK FILE: your rules and past learnings] [ACTION CAP: e.g. 3] [WHO APPROVES PAGE CHANGES] You are the Friday SEO run capped at three actions agent. Every Friday it reads a playbook file, pulls last week's search and revenue numbers, and picks at most three actions for the week instead of a long report. It updates the playbook with what it learned, and page changes stay behind your approval. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Reads the SEO playbook file at the start of each run - Pulls last week's search clicks and organic revenue - Picks at most three actions for the week - Drafts the page or content change for each action - Rewrites the playbook with what it learned What you must never do without a yes from a person: - Publishing any page change - Changing any setting in the search console Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: Claude Code, Claude Desktop with MCP, Cursor

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect Google Analytics with its own login, not yours. Grant Viewer role.
  2. 2Connect Google Docs with its own login, not yours. Grant one folder, create and edit only.
  3. 3Set up Docs site. Keep it to draft or branch access, not publish.
  4. 4Paste the prompt where your harness takes instructions. See the note under the Copy button.
  5. 5Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  6. 6Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access18 / 30

Can draft things that send or spend, so it sits close to risky actions.

Human approval30 / 30

Waits for a yes on: publishing any page change, changing any setting in the search console.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope16 / 20

Runs on its own login across 3 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Access: Take away its ability to send, post or spend. Let it only write drafts, and have a person press send or pay from their own account +6
  • Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3
  • Scope: Cut it down from 3 connected tools to the 2 it needs most, each with its own limited login instead of your full account +2

Do all of these to reach 89, up from 78.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Friday SEO run capped at three actions](https://trustcase.dev/badge/friday-seo-run-capped-at-three-actions.svg)](https://trustcase.dev/use-cases/friday-seo-run-capped-at-three-actions)
HTML
<a href="https://trustcase.dev/use-cases/friday-seo-run-capped-at-three-actions"><img src="https://trustcase.dev/badge/friday-seo-run-capped-at-three-actions.svg" alt="Trustcase trust score for Friday SEO run capped at three actions" height="20"></a>

More marketing workflows

  • Campaign credit questions with the math shown

    Ask which campaigns get pipeline credit under a named model and why one deal gave credit where it did. The agent reads attribution tables, deal journeys and data readiness checks from your own instance and writes nothing.

  • Content calendar batch that waits for you to name the rows

    On a schedule it writes a week or month of dated posts into a plain calendar file, checked against recent topics so it does not repeat. Drafting and approval are separate steps. A post goes out only after you name its row number in a live reply, and anything over two weeks old is marked stale.

  • Thursday newsletter draft that sends Sunday only if approved

    On Thursday the agent drafts Sunday's issue from the week's events and the last eight issues' results: subject, intro, up to three picks and at most one A/B test. You approve, edit, redraft or skip from your phone. Sunday sends only an approved draft, and a week with no approval is skipped with a note to you.

  • Community thread replies with promo rule checks and a daily cap

    Finds forum threads where people are asking for something your product does, ranks them by buying intent and drafts helpful replies. Each draft is checked against the community's self promotion rules, disclosure and spam signals. Posting is off by default and each reply needs your approval of the exact text, with a daily cap and cooldowns.

Other workflows that use the same tools