Get tasks doneBusiness size: Small team

A Singapore weekend smokehouse owner built his own order, prep and delivery system with Manus and now handles about 300 orders a month

Royston Chan · Singapore · Manus, Twilio WhatsApp Business API

Go to the skill

What the agent did

Manus built a prep calculator that turns the weekend's orders into how much meat and other ingredients to buy, then grew it into a system he calls FLAME. It imports website and WhatsApp orders, flags addresses with no unit number, groups deliveries by area for freelance drivers and runs a WhatsApp inbox for confirmations and feedback.

Result, as claimed

Manus reports that Mandai Smoke Co processes around 300 orders a month without hiring an admin team, and that the system was ready when the December holiday rush arrived. Chan says his drivers' hourly earnings are up to 90 SGD an hour because they follow the planned routes.

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 the public source

Try it yourself

Turn one weekend's orders into a shopping list, an address check and delivery groups before you start cooking.

Difficulty: Beginner

Prompt

Here are this weekend's orders with item, quantity, delivery slot and address: [paste]. Here is how much raw ingredient each menu item needs, and the cooked yield where it matters: [paste]. Do three things. 1. Total the raw ingredients I need to buy, with a small buffer of [percent] and the maths shown. 2. List any address that looks incomplete, such as a condo or flat with no unit number, so I can ask the customer. 3. Group the deliveries by area and slot into [number] driver runs, with a suggested order for each run. Mark anything you are unsure of as [check]. Return a draft only. Never send, spend, change settings or write to a live system.

Prompt: starter by Solopreneur Code

Tools

  • Manus Used to build the prep calculator and the FLAME order, delivery and customer message system.

Steps

  1. Write down how much raw ingredient each menu item uses.
  2. Export one weekend of orders from your website or chat.
  3. Run the prompt and compare the shopping list with what you bought last time.
  4. Message customers whose addresses are flagged before delivery day.
  5. Once the list works, ask an AI builder to turn it into a small tool you can reuse.

Watch out: A wrong yield or recipe number throws off the whole shopping list, so check the first few weekends against what you actually used.

Starter version by Solopreneur Code

Skill: Orders and admin

Add this skill

Orders and adminDifficulty: Beginner

Weekend order prep list and delivery runs

Turns a weekend's orders into a raw ingredient shopping list, a list of incomplete addresses to fix and delivery runs grouped by area.

Works with
Claude, ChatGPT, Gemini Works as plain instructions in any AI chat. Check the yields against what you really used.
Tools in the story
Manus
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.

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: Small teamIncludes prompt

A Singapore industrial supplier's CEO built a working CRM with an AI agent in two hours, after a S$25,000 one at a previous company went unused

Erick Villalobos (Evermove Engineering & General Supplies) · Singapore · Manus

Erick Villalobos acquired Evermove Engineering, a 52-year-old Singapore industrial supplies company, with 12 years of transaction records, about 1,000 customer accounts and no data team. He described the problem to Manus, an AI agent, in plain English: which customers to call, when and in what order. Manus offered several options, including a custom CRM. After a week of daily use and fixes it was producing the sales team's weekly call schedule, and he keeps improving it each month. The account is written by NUS Business School, where he took an AI course.

Result, as claimed

"Two hours later, a working version of the CRM was running on Evermove’s real company data." "Total budget: zero." A CRM at a previous company "cost S$25,000 and was abandoned on the first day".

Save moneyBusiness size: Small teamIncludes prompt

Rebel Cheese CEO Kirsten Maitland says an invoice checker she built with Claude and Manus has saved $400,000 in shipping overcharges in a year

Kirsten Maitland · United States · Claude, Manus

Claude read a year of carrier invoices against the shipping contract and found where the overcharges came from. Manus then built a one-page tool that compares each weekly invoice line to the contract rates, flags any charge more than ten cents over and prepares the credit request.

Result, as claimed

Fortune reports that Maitland estimates the carrier overcharged about $250,000 after the holiday season and that the agent has saved $400,000 in one year. She told Fast Company the company now saves $1,500 to $4,000 a week, pays about $200 a month for Claude and Manus, and that the carrier has credited every claim so far.

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.