Get tasks doneBusiness size: Small team

A heritage kueh maker in Singapore cut a full day of order tallying to two hours with an AI system that reads hotel purchase orders

Alan Tan (HarriAnns Nonya Table) · Singapore · Custom AI ordering platform (Knovel Engineering)

Go to the skill

What the agent did

Alan Tan is the third generation owner and CEO of HarriAnns Nonya Table, which supplies kueh to hotels and runs eight cafes. In March 2025 a hotel's 2,000 kueh order was missed because pages of its purchase order were not printed. Tan had Singapore consultancy Knovel Engineering build an AI platform that reads purchase orders from email, recognises the naming variations of over 120 products, tallies the next day's production and flags unusual ordering patterns. It went live in June.

Result, as claimed

"That reduced a whole day's work for my admin staff to just two hours. They just have to spend time checking the AI's output," said Tan. The system cost less than $50,000 to develop, and an Enterprise Development Grant covered half.

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 Alan Tan's story in The Straits Times

Try it yourself

Before paying for a custom build, test whether an AI chat can turn a day of purchase orders into one production tally.

Difficulty: Intermediate

Prompt

Here is my product list with codes and the other names customers use for each item: [paste]. Here are today's purchase orders: [paste or attach]. Match every line to a product code, then give me one table with the total quantity of each product for [delivery date]. List any line you could not match as CHECK. Then compare with these usual orders from regular customers [paste] and point out anyone who left out an item they normally order.

Tools

  • ChatGPT Our pick for testing the idea cheaply. HarriAnns used a custom platform built by Knovel Engineering

Steps

  1. List your products with every other name customers use for them.
  2. Run one day of purchase orders through the prompt.
  3. Check the totals against the orders by hand for a week or two.
  4. Only then decide whether a custom system is worth paying for.

Watch out: Purchase orders can run to many pages, and that is how HarriAnns missed one. Check the AI's totals against the source orders and keep a person signing off before production.

Starter version by Solopreneur Code

Skill: Orders and admin

Add this skill

Orders and adminDifficulty: Intermediate

Purchase order production tally

Matches every line on a day of purchase orders to your product codes, totals each product and flags regular customers who left something out.

Works with
Claude, ChatGPT, Gemini Needs an AI that reads PDF or email attachments, or paste the text. HarriAnns used a custom platform. This is a cheap way to test the idea first.
Tools in the story
ChatGPT
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: turn chat messages into orders

Other tools for this job

Tools used

  • Custom AI ordering platform (Knovel Engineering)See official pricing

Proven in other stories

Could also do this

  • Take App Not tested in a storyAn online store for WhatsApp. Says it turns chats into structured orders, with a dashboard to track order status and payments. Free plan up to 50 orders a month.Page checked 2 November 2026. Vendor page: Take App, 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

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.