StartAtende

A WhatsApp support agent that also tells the business what customers want.

Role: Founder, design and engineering
Status: In production
Stack: LLM agents · WhatsApp · intent routing · sentiment analysis
Link: startatende.com ↗

01The problem

A support agent that only answers throws away the most honest data a business has: what its customers actually say.

02What I built

AI customer support on WhatsApp with intent routing. Then the agent's own conversations with users, customers and leads are analyzed for sentiment, product gaps, business opportunities and market signals. The agent does not just answer, it becomes a source of product decisions.

03The decision that mattered

Cost is tracked per conversation, not per API call, because a conversation is the unit a business can actually price against.

04Receipts

Intent routing on WhatsApp
Cost per conversation, including model cost
Sentiment, FAQ gaps and business insights over the agent's own conversations
An MCP server exposes all of it to your assistant

05MCP

Ask your support operation questions: performance, sentiment, FAQ gaps, model cost, top intents. · Remote MCP connector

get_overview
get_agent_performance
get_business_insights
get_faq_gaps
get_model_costs
get_sentiment_trend
get_top_intents
get_top_clients
get_products
get_payment_summary
list_conversations

06Stack

LLM agents
WhatsApp
intent routing
sentiment analysis
MCP

Visit startatende.com

Next case SunoBoard An AI music studio that an agent can run on its own.