Skip to content

Content drafts that learn rules from your approval notes

A small team of agents researches, drafts, fact checks and plans content for each of your brands from a brand file and real examples of your voice. When you approve a draft with a note, the note becomes a rule every agent reads first. It only writes drafts and nothing is published on its own.

MarketingWorks with Claude Code · Cursor+1Community example

What it does

  • Finds timely ideas with a capped number of searches
  • Drafts in your voice from your real examples
  • Checks every claim against sources before you see it
  • Adapts one draft for each platform
  • Turns your approval notes and weekly stats into standing rules

Your approval boundaries

Approval required

These actions always wait for your yes:

  • Publishing or scheduling anything
  • Changing a brand's facts file

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 finds timely ideas with a capped number of searches. Next, it drafts in your voice from your real examples. Then it checks every claim against sources before you see it. After that, it adapts one draft for each platform. Finally, it turns your approval notes and weekly stats into standing rules. It works with your web search, docs and analytics, 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 or scheduling anything and changing a brand's facts file, and says plainly if a step cannot be undone.

“It only writes drafts. A human approves everything.”
Shrimanth Polamuri bugbugbuget04 on GitHub · Nov 4, 2026
Before you startWeb search · Docs accessScoped permissionsClaude Code or Cursor
Explore required tools and model recommendations

Tools and access

  • Web search

    Handles the web search part of this job. Grant public search results only.

    API required: Optional. Built into most agent harnesses. A standalone search API needs its own key.

    No sign-up needed
  • 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.

  • 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.

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.

one folder each

2Your prompt

4 of 4 still empty
Fill these in before you run it: [BRANDS: one folder each] [BRAND FACTS AND VOICE EXAMPLES] [PLATFORMS] [SEARCH CAP PER IDEA RUN] You are the Content drafts that learn rules from your approval notes agent. A small team of agents researches, drafts, fact checks and plans content for each of your brands from a brand file and real examples of your voice. When you approve a draft with a note, the note becomes a rule every agent reads first. It only writes drafts and nothing is published on its own. 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: - Finds timely ideas with a capped number of searches - Drafts in your voice from your real examples - Checks every claim against sources before you see it - Adapts one draft for each platform - Turns your approval notes and weekly stats into standing rules What you must never do without a yes from a person: - Publishing or scheduling anything - Changing a brand's facts file 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, Cursor, Custom GPTs

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. 1Set up Web search. Keep it to public search results only.
  2. 2Connect Google Docs with its own login, not yours. Grant one folder, create and edit only.
  3. 3Connect Google Analytics with its own login, not yours. Grant Viewer role.
  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 or scheduling anything, changing a brand's facts file.

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 Content drafts that learn rules from your approval notes](https://trustcase.dev/badge/content-drafts-that-learn-rules-from-your-approval-notes.svg)](https://trustcase.dev/use-cases/content-drafts-that-learn-rules-from-your-approval-notes)
HTML
<a href="https://trustcase.dev/use-cases/content-drafts-that-learn-rules-from-your-approval-notes"><img src="https://trustcase.dev/badge/content-drafts-that-learn-rules-from-your-approval-notes.svg" alt="Trustcase trust score for Content drafts that learn rules from your approval notes" height="20"></a>

Other workflows that use the same tools

  • Weekly ops report

    Operations. Writes the Monday numbers summary so you do not build it by hand.

  • Ideal customer profile builder

    Sales. Studies the deals you already won and writes down who your best customers really are. You get clear filters for new leads and a list of warning signs.

  • Job application drafter

    Personal. Searches job boards for roles that fit your profile and drafts a tailored CV and cover letter for the ones you pick. A second pass checks the drafts against your real experience so nothing is made up.