Get tasks doneBusiness size: Small team

Singapore caterer lets an AI agent take standard WhatsApp orders, and its vendor reports order admin time down about 85%

Belicia Tan · Singapore · Odello (eAI by TreeDots), WhatsApp

Go to the skill

What the agent did

Odello reads customer orders sent on WhatsApp, uses the customer's history and the catering menu, asks clarifying questions, prices and confirms standard orders and enters them into the order system. It also helps staff draft non-standard replies and tracks delivery ETAs and proof of delivery.

Result, as claimed

eAI reports that two months after go-live around 92% of incoming orders are handled end to end by AI, order admin time is down about 85%, and around 30% of orders now arrive between 9pm and 9am.

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

Test whether an AI can turn your messy chat orders into priced draft orders before you automate anything.

Difficulty: Intermediate

Prompt

I run [type of food business]. Here is my menu with prices: [paste]. My delivery rules: [paste]. Orders over [amount] or with [special cases] always need my approval. Here are [5] real customer messages with names and numbers removed: [paste]. For each message, pull out headcount, date, time, delivery address area and dietary needs. Match only items on my menu and show the price sum line by line. List what is missing as questions for the customer. Mark anything that needs my approval. Do not invent items, prices or delivery slots. Return a draft only. Never send, spend, change settings or write to a live system.

Prompt: starter by Solopreneur Code

Tools

  • Odello Source-named tool. Official product URL not independently verified during intake, omitted.

Steps

  1. Copy five recent order messages and remove names and phone numbers.
  2. Paste them with your current menu and delivery rules into the prompt.
  3. Check every item and price against your menu.
  4. Note which messages needed a human and why, before you consider any automation.

Watch out: A wrong dietary note or delivery time can ruin an event. Keep a person checking every confirmed order until you trust the results.

Starter version by Solopreneur Code

Skill: Orders and admin

Add this skill

Orders and adminDifficulty: Beginner

Catering order draft and exceptions

Turns chat orders into priced draft order records against a fixed menu, with questions for the customer and an exceptions list for the owner.

Works with
Claude, ChatGPT, Gemini Text-only starter. No connector or script tested. Copy business inputs manually and review outputs.
Tools in the story
Odello (source tool), WhatsApp (source channel)
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: SoloIncludes prompt

A consultant running two companies hands his tax letters, bank queries and company filings to AI agents and says they saved him at least 2 days in a month

Peter Hartree @peterhartree · Country unknown · Claude Code, Codex, Gmail, WhatsApp, Google Drive

He sends a screenshot, PDF or forwarded message with a short request. The agents have access to his Gmail, WhatsApp and Drive and can use a browser. Examples he lists: tracing an unexplained bank seizure to a tax charge, checking a tax portal and posting a document by registered mail, reviewing and approving year-end company accounts, and flagging terms in a merger engagement letter that contradicted what was agreed by email.

Result, as claimed

He estimates the AIs saved him at least 2 days of work over the past month. He says the error rate seems similar to or lower than his own and that agents rival a human PA for many tasks.

Get tasks doneBusiness size: CompanyIncludes prompt

A Singapore phone retailer with 20 outlets merged its customer data into an AI CRM and estimates it saves about 120 staff hours a day

Alan Tan · Singapore · Unnamed AI-enabled CRM, WhatsApp

A custom system consolidated and deduplicated records, populated profiles, supported segmentation and chatbot responses. Fixed automation sent reservation confirmations.

Result, as claimed

Mister Mobile estimates it saves about 120 man-hours of manual work a day by automating data consolidation, customer replies and marketing broadcasts, after merging more than 585,000 customer records and 1.05 million orders.

Get tasks doneBusiness size: Small teamIncludes prompt

Kai Yang cut Cake Inspiration WhatsApp replies from a 9-hour median to about 5 seconds with a shop agent

Kai Yang (Cake Inspiration) · Singapore · WhatsApp, Volty / Voltade agent

Volty built Cake Inspiration a WhatsApp agent that answers from the shop site, routes catalog shoppers to product pages, hands custom orders to a human, and learns from staff corrections Kai Yang approves.

Result, as claimed

Voltade's 2 Nov 2026 case study says Cake Inspiration was answering about 90 WhatsApp inquiries a day by hand with median reply time up to 9 hours. The WhatsApp agent now answers from the shop knowledge base, points catalog shoppers to product pages, and hands custom orders to a human designer. Key results shown: median reply time 9 hours to 5 seconds, and 7 staff corrections applied in week one with no engineer in the loop. Founder Kai Yang is quoted saying he can fix the agent himself by telling it what he disliked about a reply.