Get tasks doneBusiness size: Small team

A non technical founder in Jakarta used AI agents to build a cash register app for his cookie booth that took real money on day nine

Lucas Zhu (Frollie) · Indonesia · AI coding agents (not named in source)

Go to the skill

What the agent did

Lucas Zhu, an ex-McKinsey founder with no engineering background, ran a group of AI agents like a small team to build a point of sale app for the Frollie cookie booth in Block M, South Jakarta. It covers staff sign in, stock, sales, QR and bank transfer payments, receipts and manager approvals on Telegram. He wrote his own review and testing workflows because, he says, the agents did not catch everything.

Result, as claimed

"Fifteen days ago this was a planning doc. Today it takes real money at our cookie booth in Jakarta, and I hired no engineers to get there." His deck lists idea to live in 12 days, 500+ automated tests and taking real money on day 9.

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

Proof

See Lucas Zhu's Frollie POS talk and speaker notes

Try it yourself

Before an AI coding agent builds anything that handles money, have it write a plan and review that plan against a checklist.

Difficulty: Advanced

Prompt

I want to build [small app, for example a simple order and payment tracker] for [my business]. Do not write code yet. First write a plan: the screens, the data you store, how a payment is confirmed, what happens on a double tap or dropped connection, and how a refund is recorded. Then review your own plan as a senior engineer and list gaps under Critical, Improvement and Refinement, including rollback and tests. Wait for my OK before building.

Tools

  • shipshape His open source plan review skill for AI coding agents, linked from the talk as his most used skill

Steps

  1. Write a one page plan of what the app must do before any code.
  2. Have the agent review the plan and fix the critical gaps.
  3. Build in small pieces and test each one with real cases.
  4. Run a few real transactions by hand before trusting it with customers.

Watch out: Passing tests can still hide bugs in payment flows, so test the real money path end to end and keep a manual fallback.

Starter version by Solopreneur Code

Skill: Build with a coding agent

Add this skill

Build with a coding agentDifficulty: Advanced

Plan review before code

Makes a coding agent write a plan for a small money-handling app and review it for gaps before it writes any code.

Works with
Claude Code, Codex, Claude, ChatGPT Works in any AI that can plan. The story's agents are not named. His own plan review skill, shipshape, is open source.
Tools in the story
shipshape
Country
Indonesia

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: build your own business app

Other tools for this job

Tools used

  • AI coding agents (not named in source)See official pricingProduct not named, so no price line.

Proven in other stories

Could also do this

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

Once a week it reads his spam and archived email, groups it by sender and looks for events and articles that fit his goals for the year. For each useful sender it gives up to 5 action points and suggests pulling it out of spam or unsubscribing. It now checks his calendar and working hours before it shortlists events. Claude also names new files and chats to one convention and drafts unusual workshop formats for him to pick from.

Result, as claimed

The first run went through 718 emails and it now handles about 30 a week. He says AI gives him back 3 to 4 hours a week, and one webinar it flagged put him on a path to new work.

Get tasks doneBusiness size: SoloIncludes prompt

A marketing educator has Claude route her inbox into CRM deals, tasks and draft replies, and says agents save her 3 to 4 hours a week

Cristina Peñaloza Morales · Country unknown · Claude, Gmail, HubSpot, Todoist, Notion, Riverside, Gamma

Reads new email and routes each one. Training enquiries become a HubSpot contact and deal with a drafted reply. Community messages get a draft reply. Possible collaborations become a Todoist task. Invoices and admin get a label. Also runs a scheduled Monday AI news digest.

Result, as claimed

She says agents save her between 3 and 4 hours a week.

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.