---
title: "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"
person: "Erick Villalobos (Evermove Engineering & General Supplies)"
tools:
  - "Manus"
country: "Singapore"
category: "Get tasks done"
category_slug: get-tasks-done
proof:
  - label: "Read the NUS Business School story on Erick Villalobos"
    url: "https://bizfaculty.nus.edu.sg/ai-showcase/from-the-classroom-to-the-crm-how-a-non-technical-ceo-built-ai-tools-that-run-his-company-every-week/"
date: 2026-10-30
date_posted: 2026-08-17
as_claimed: "The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome."
url: "https://agentstories.org/stories/erick-villalobos-evermove-manus-crm.html"
markdown_url: "https://agentstories.org/stories/erick-villalobos-evermove-manus-crm.md"
site: "Agent Stories by Solopreneur Code"
---

# 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

## What the agent did

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".

> The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome.

## Proof

- [Read the NUS Business School story on Erick Villalobos](https://bizfaculty.nus.edu.sg/ai-showcase/from-the-classroom-to-the-crm-how-a-non-technical-ceo-built-ai-tools-that-run-his-company-every-week/)

## Try it yourself

Describe your customer list to an AI agent and have it build a simple tool that tells you who to call this week.

Prompt:

```text
I run [type of business]. Attached is my sales history: [file with customer, date, product, amount]. Build me a simple CRM I can open in a browser. For each customer show the last order date, usual order gap, total spend in the last 12 months and whether they are overdue to reorder. Then make a weekly call list of the top [20] customers to contact, in order, with one line on why each is on the list. Use only the data in the file. Explain how you ranked them so I can change the rules.
```

Tools:

- [Manus](https://manus.im): The AI agent he used to build the CRM
- [Claude](https://claude.ai): Alternative that can build a similar tool from a spreadsheet

Steps:

1. Export your sales history to a spreadsheet and remove anything you are not allowed to share.
2. Give it to the agent with the prompt.
3. Check the call list against customers you know well.
4. Use it for a week, then ask for one change at a time.

Watch out: Your customer data goes to the AI service, so check its data terms and Singapore's PDPA before uploading, and keep a copy of the data outside the tool.

## More

- [This story as a web page](https://agentstories.org/stories/erick-villalobos-evermove-manus-crm.html)
- [More stories: Get tasks done](https://agentstories.org/categories/get-tasks-done.html)
- [More stories from Singapore](https://agentstories.org/countries/singapore.html)
- [More stories that use Manus](https://agentstories.org/tools/manus.html)
- [Every story, indexed for AI assistants](https://agentstories.org/llms.txt)
