Customer Service · Blog · 🇧🇷 Brazil
A family business answers leads with an AI agent on WhatsApp
A transformer factory in São José do Rio Preto deployed an agent to answer questions and collect the details needed for a quote.
- Profession
- Business Owner, Salesperson
- Tools
- Meta Business Agent
- Source
- whatsappbusiness.com ↗
- Country
- 🇧🇷 Brazil
- Report date
- July 2, 2026
- Verified on
- October 24, 2026
What they did
The owner, with no AI experience, turned on Meta's agent to answer customers at any hour.
How it went
The company says it now sends up to six times more quotes per day and that 90% of interactions stayed with the agent. The numbers were released by the company itself in a Meta case study.
Good to know
Review the technical answers: price and lead time should go through a person.
The prompt
List the 15 questions my customers of [technical service] ask most often and write a short answer for each one. Include which details to ask for in order to prepare a quote.
Replace what is in [brackets]. Prompt written by us from the account, not a literal copy of the source. Do not paste other people’s personal data (privacy laws such as LGPD and GDPR apply).
Summary in our own words. Results as stated in the original account; we have not tested or audited them. Read the source ↗ Found a mistake?
Similar cases
01Small-town cosmetics brand creates a hair care assistant on WhatsApp
Zafir Cosméticos, from Jacobina (BA), created Zaia, which guides customers and hairdressers by hair type.
02Clinic automates appeals of health insurance claim denials
An n8n workflow pulls the patient record when a claim is denied and AI drafts the appeal using the clinical data.
03Requesting an exchange for defective clothing from a photo
A photo of the torn pants, a receipt found in Gmail and an email to the store, ready to review.
04Agent navigates the insurer's phone menu until it finds a human
To change a policy, the user had the agent make the call and transfer only once a representative was available.
05Support triage with draft replies for review
A five-node workflow classifies each email, rates its urgency, summarizes it and writes a reply for a human to approve.
06British car dealer group automates its customer service SMS
Stellantis &You UK closes out messages that need no action and flags unhappy customers.
07TELUS analyzes every call to fix problems before customers complain
The Canadian carrier anonymized conversations and used AI to find sentiment and root causes.
08Stopping your WhatsApp agent from duplicating customers in the CRM
A post shows why agents write to the wrong record: accents, invisible characters and stylized names.