Get tasks doneBusiness size: Small team

An agency founder runs his own site's marketing through Claude Code and says the weekly work fell from about 25 hours to about 5

Dhawal Shah (2Stallions) · Singapore · Claude Code

Go to the skill

What the agent did

Dhawal Shah runs 2Stallions, a regional digital marketing agency. For most of 2026 he has run his own marketing through Claude Code, connected to his tools through their APIs. On his own site it handles the website, SEO, analytics, newsletter, social and video. Each Monday he asks one question about what changed across the site, search, ads and newsletter and gets an answer in about a minute. On the agency side it only runs ad reporting across five platforms, after a privacy and terms of service review. He signs off anything that spends money.

Result, as claimed

"The recurring work of running every channel used to take me about 25 hours a week. It now takes about five." A weekly cross platform ad report went from four to six hours to about 30 minutes, and a LinkedIn content pack from three or four hours to about 30 minutes. The stack costs about US$250 a month on AI.

This is the result as claimed in the public source linked below. It has not been checked and is not a typical outcome.

Proof

Read Dhawal Shah's account on e27

Try it yourself

Ask one weekly question across all your marketing data instead of opening every dashboard.

Difficulty: Advanced

Prompt

Every Monday, pull last week's numbers from [site analytics], [search console], [newsletter platform] and [ad accounts] using the API keys in my config. Then tell me: 1. What changed most versus the week before and the likely cause. 2. Which search queries moved. 3. Where new subscribers came from. 4. Anything that looks wrong in the data. Show the numbers behind every claim and do not change any settings or budgets.

Tools

  • Claude Code Named in the story. He runs his marketing through it and connects tools by API

Steps

  1. Start with your own accounts and your most boring weekly report, not a client's.
  2. Get read only API access for each platform. Expect some approvals to take days.
  3. Run the prompt each Monday and check its explanations against the raw numbers.
  4. Keep a short instruction file and prune it monthly so old notes do not mislead the agent.

Watch out: It will always offer an explanation for a change, even a wrong one. Check the cause yourself and keep a human sign off on anything that spends money.

Starter version by Solopreneur Code

Skill: Marketing

Add this skill

MarketingDifficulty: Advanced

Monday marketing question

Pulls last week's numbers from your analytics, search, newsletter and ad accounts and answers what changed, with the numbers behind each claim.

Works with
Claude Code, Claude, ChatGPT The story used Claude Code with read-only API access. In a normal AI chat, paste last week's exports instead.
Tools in the story
Claude Code
Country
Singapore

How to use this: Copy the skill, paste it into Claude, ChatGPT or Gemini, and ask it to save it as a skill. If it cannot, it will still follow the steps.

Show skill

If the Copy button does not work, select this text and copy it.

Job: write and run marketing content

Other tools for this job

Tools used

Could also do this

  • Jasper Not tested in a storySays its AI agents write SEO content, campaigns, social posts and email in your brand voice. Free trial. Aimed at company marketing teams.Page checked 2 November 2026. Vendor page: Jasper, opens in a new tab

Sign up for the newsletter

Get the next story from Solopreneur Code in your inbox.

Form not loading? Subscribe on Substack

Back to all stories

More like this

Browse all stories
Get tasks doneBusiness size: SoloIncludes prompt

A newsletter writer's Claude Code agent turned screenshots into 38 scheduled Substack Notes he did not write, with no engagement lift

Dheeraj Sharma @genaiunplugged · Country unknown · Claude Code, SubflowAI Substack connector, macOS scheduler, Substack Notes

Each morning a headless Claude Code run takes the oldest screenshot, classifies it, writes a 45 to 115 word Note in his voice, checks it against copy gates, uploads the image, schedules it for the next free day, reads the schedule back and archives the screenshot. Screenshots with emails, phone numbers or orders are set aside.

Result, as claimed

29 Notes scheduled by 23 Sep and 38 by 12 Oct with none written by him. 12 measured Notes had a median of 3.5 likes against 5 for his other Notes, which he reads as no lift.

Get tasks doneBusiness size: SoloIncludes prompt

A Fukuoka developer had Claude Code build a bookkeeping pipeline that reconciled 200 transactions and flagged its own doubts

Ken Imoto @kenimo49 · Japan · Claude Code, MCP connection to his accounting platform (platform not named)

Built a re-runnable pipeline that pulls the month's transactions over MCP, matches bank rows to receipts by amount and date, proposes a category with a one-line reason for each row and flags rows it isn't sure about.

Result, as claimed

200 transactions reconciled and 11 miscategorised, a 94.5% hit rate. Review shrank to 18 flagged rows plus a sample. 7 of the 11 errors were in the flagged pile and 4 were caught on the sample.

Get tasks doneBusiness size: CompanyIncludes prompt

A Malaysian point-of-sale company runs about 170 AI agents its co-founder built, and sales admin per lead fell from about 15 minutes to about 1

Fong Wai Hong · Malaysia · Claude Code, Salesforce

When someone books a demo, an agent researches the shop and briefs the caller. Other agents rank every open lead into a live call list that re-sorts about every 30 seconds, so a promised callback rises to the top. After each call the conversation is transcribed and the lead record is filled in. He also replaced a couple of hundred Zapier automations with his own stack in about four weeks.

Result, as claimed

Fong says the average time to close out a lead is now about 1 minute, down from about 15. He says reps make two times more calls a day and meetings booked per 100 leads went up about 25%, which he says shows up in the bottom line. He says the marketing team used to spend 30 to 40% of its time fixing broken Zaps.