Aurra · Imitate Labs

WhatsApp AI Chatbot & Team Inbox

A WhatsApp agent that replies to customers in seconds using what the business knows, and passes the chat to a person when it should.

Usage & cost per AI call and Meta message
WhatsApp reports: daily volume, 6 s median bot reply, delivery rates
Median AI reply time (production, 30 days)
6 s
Replies, text and voice notes
24/7

Platforms

  • Web
  • WhatsApp

Overview

Aurra's WhatsApp agent replies to every customer message within seconds, at any hour, using the business's own knowledge library. When a chat needs a human, it hands over. Alongside it we built a team inbox, lead scoring, broadcasts and reports, so the sales team spends its time on the chats that need a person.

Project details

Client
Imitate Labs (product: Aurra)
Industry
AI / SaaS: sales and support automation for Indian businesses (real estate, education, healthcare, lending…)
Market
India (11 languages)
Engagement
Jan 2026 – present
Our role
All of it: product, voice AI pipeline, WhatsApp bot, CRM, billing, cloud
Platform
Web app + WhatsApp (Meta Cloud API)

What we built

  • One AI persona per WhatsApp number, replying 24/7 to text and voice notes
  • Knowledge library: brochures, price lists, Q&A, notes and links; answers only from what's in it, and lists unanswered questions
  • Team inbox with AI replying / needs a person / with a person, assignment and private notes
  • Lead scoring: rule-based Hot / Warm / Cold with ready-made templates (real estate, education)
  • Template management and broadcasts
  • Reports: delivered, read, replied, failed, bot and agent reply times
  • Usage and cost tracking per conversation

Inside the product

WhatsApp reports: daily volume, 6 s median bot reply, delivery rates
Usage & cost per AI call and Meta message
Chat leads with temperature and last outcome
Knowledge library the agents answer from
01 / 04

WhatsApp reports. Daily volume, 6 s median bot reply, delivery rates

Technology

Tech stack

  • Meta WhatsApp Cloud API
  • Google Gemini
  • NestJS
  • PostgreSQL
  • Next.js

Want a product like this?