A WhatsApp conversation goes quiet after three messages. The rep sends “Just checking in”. That is ignored too.
AI solution 07 · Engagement and conversion
Conversations that go quiet mid-thread
Follow-ups written from what was actually discussed, then, if those are ignored, the most relevant case study or video instead of more text.
AI agent · WhatsApp
Two stages. First, a follow-up written from what was actually discussed, adding something new rather than “are you there?”, sent after a set delay with a limit on attempts. If that is ignored too, the system stops sending text and picks the most relevant case study, product video or brochure from the media library instead.
Conversations that would have died restart on their own, and some convert weeks later because the right document stayed in their WhatsApp.
The problem
Sending more text starts to feel pushy, so the rep stops. The lead goes cold for good, even though the interest was real a week earlier.
Why it happens
- Generic follow-ups add nothing new, so there is no reason to reply.
- Reps have too many threads to remember what each buyer actually asked about.
- After two ignored messages, most teams have no next move other than giving up.
How the system works
- 01
Notice the silence
When a conversation goes quiet mid-thread, a timer starts. By default the first follow-up waits around two hours.
- 02
Follow up with something new
Each follow-up refers to what was actually discussed and adds value: an answer, a detail, a relevant point. Attempts are capped, three by default.
- 03
Switch from text to content
If follow-ups are ignored, the system stops writing and chooses the most relevant asset from your media library, such as a case study, product walkthrough or brochure.
- 04
Hand back to the rep
Any reply goes straight back to the owning rep with the full thread, so the conversation picks up where it left off.
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.
Writing the follow-up
A message that refers to the actual conversation needs the AI to read the thread and write something useful.
Choosing the asset
Matching what the buyer discussed to the right document or video is a judgement on text.
Timing and limits
Delays, attempt caps and quiet hours are rules, so the system never becomes spam.
What changed
- Conversations that would have died restart without a rep chasing them.
- Cold leads get one more genuinely useful touch instead of being abandoned.
- Some leads convert weeks later, because the relevant document stayed in their WhatsApp.
Works with your stack
Works with any approved WhatsApp provider and your existing media library, and logs every touch in the CRM.
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 this annoy buyers?
It is designed not to. Every message adds something new, attempts are capped, and the switch to content replaces more text rather than adding to it.
Can we control the delay and number of attempts?
Yes. Two hours and three attempts are defaults. Both, plus quiet hours, can be set per pipeline or product.
What if we do not have much content?
Even a few good assets are enough to start. The system also shows which assets restart conversations, which tells you what to make next.
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
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.
Read the case study →08 · Engagement and conversionBulk WhatsApp sends that get the number blockedWhatsApp campaigns sent only to leads that fit, never twice, and inside the platform’s safety limits, so volume does not cost you the account.
Read the case study →02 · Lead captureA missed call becomes a lost leadThe 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 →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.