A serious enquiry lands at 11 PM on WhatsApp. The rep sees it on Monday morning. By then the buyer has messaged three other suppliers, had answers from at least one of them, and no longer remembers which company was which.
AI solution 01 · Lead capture
The midnight WhatsApp enquiry
A WhatsApp AI agent that answers every enquiry in under 30 seconds, at any hour, asks the qualifying questions and passes the lead to a rep only when it is worth a call.
AI agent · WhatsApp
An AI agent on WhatsApp that replies in under 30 seconds, asks the qualifying questions, captures requirement and budget, and hands over to a person only when the lead is worth a call.
First response goes from hours to seconds. Qualified leads reach the rep with the conversation already started.
The problem
Nobody did anything wrong. The rep was off shift, the enquiry came in through a channel nobody was watching, and the first reply simply came too late to matter.
Why it happens
- Buyers message when they are researching, which is often evenings and weekends, not when the sales team is at its desk.
- WhatsApp enquiries sit in a phone or a shared inbox with no owner and no response clock.
- When the reply does come, the rep starts from zero: no requirement, no budget, no idea whether the lead is worth a call.
How the system works
- 01
Instant reply
Every incoming WhatsApp message gets a reply within seconds, written for the product or page the buyer came from rather than a generic greeting.
- 02
Qualifying conversation
The agent asks the questions your best rep would ask: what they need, for what application, in what quantity, by when, and with what budget. It answers routine product questions from your own knowledge base.
- 03
Decision to hand over
Against criteria you define, the agent decides whether the lead needs a person now, can wait for working hours, or is not a fit. Only the first two reach a rep.
- 04
Clean handover
The lead is created or updated in the CRM with the full conversation, the answers captured and the reason for the handover, so the rep starts the call already knowing the requirement.
Where AI does the work
Rules first, AI second. The model runs only where judgement on text is needed, so running costs stay low as volume grows.
Conversation and qualification
Understanding free-text messages, asking the next sensible question and judging fit is language work, so the agent does it.
Routing and CRM updates
Assigning the lead by territory or product, creating the record and logging the chat follow fixed rules and run as plain code.
The sales call
Pricing, negotiation and anything a buyer would notice being wrong stay with the rep.
What changed
- First response time goes from hours, sometimes days, to seconds.
- Qualified leads reach the rep already warmed up, with requirement and budget captured.
- Reps stop spending calls on enquiries that were never a fit.
Works with your stack
Works with any approved WhatsApp provider, including the Meta Cloud API, Gupshup, Interakt, Wati, AiSensy and Twilio, and writes to Zoho, HubSpot, Salesforce, Pipedrive or Freshworks.
Nothing is replaced. It is a layer on top of the tools you already use, built on your accounts, so the data stays yours.
Questions
Will buyers know they are talking to AI?
We recommend being open about it. Buyers mostly care that they got a useful answer quickly, and a clear handover to a named person when it matters builds more trust than pretending.
What if the agent gets a question it cannot answer?
It says so and hands over to a person rather than guessing. Questions on pricing, custom terms or anything outside the knowledge base are routed to a rep by design.
Do we need to change our WhatsApp provider?
No. The agent connects to the provider you already use, as long as it is an approved WhatsApp Business provider with an API.
What does it cost to run?
We build it in your own environment, and the AI runs on your own Google (Gemini) or OpenAI account. You pay them directly, pay as you go, only for what is used. We add no markup and charge nothing per message or per seat. Because rules handle most of the work before any model is called, the AI bill stays small.
Running cost and data
What it costs to run
We build the system in your own environment. You pay only for the AI it uses, directly to the AI provider, with no markup from us.
The system is set up in your own cloud account. Conversations, recordings and CRM data move between your systems and the AI provider you choose. They do not pass through our servers or a separate chatbot platform.
The AI runs on your own account with Google (Gemini) or OpenAI. You pay them directly, only for what is used, at their published rates.
We do not resell AI usage or charge per message, per conversation or per seat. Our fee is for building and improving the system, and it is agreed upfront.
Rules and plain code do most of the work, and the model is called only where judgement on text is needed, so the AI bill stays small as volume grows.
WhatsApp and calling charges, where they apply, are billed by your provider as they are today.
Related solutions
The calling system linked to WhatsApp, so every unanswered sales call gets a personal message within seconds and an AI keeps the conversation going until a rep is free.
Read the case study →03 · Lead captureThe anonymous website visitorA website chat that opens only when a visitor shows real buying intent, answers from your own knowledge base, and sends the lead to the CRM with every page and question attached.
Read the case study →06 · Data quality and qualificationEvery rep qualifies differentlyYour qualification criteria written down once and applied by AI to every lead the same way, with a score, the reasons behind it and a recommended next step.
Read the case study →Sound familiar?
Thirty minutes is enough to map where leads come from and where they drop off. If there is a fit, you get a short written diagnosis of the two or three problems worth fixing first, with a rough investment range.