Analytics, return on spend and AI
Numbers that say whether it worked, and an AI that reads them.
Every status change is stored as an immutable event, so every figure traces back to a message. Costs use Meta's own daily figures, not an estimate.
- Sent4,600
- Delivered4,41896%
- Read3,12771%
- Clicked1,39845%
- Replied61244%
- Converted27645%
₹3,609 spent at Meta’s rate · ₹4.6L attributed from 276 conversions posted by the store · ₹13.08 per conversion
What it is
WhatsApp campaign analytics show what happened after send: delivered, read, clicked, replied and, when a business posts its conversions, converted, with the rupee cost of the campaign beside them. This product keeps every message status change as an immutable event, pulls Meta's own daily cost figures, attributes conversions to the campaign, journey and Click-to-WhatsApp ad that earned them, reports them back to Meta's Conversions API, and adds an AI layer that summarises conversations, suggests replies, translates, writes templates and turns the numbers into plain-language insights.
What it does
Every line below is in the product today. The ones marked only here were not found in WATI’s, AiSensy’s or Interakt’s public documentation on 20/09/2026.
Funnel with cost per stage
Sent, delivered, read, clicked, replied, converted, with failure reasons and the rupee cost of the campaign.
Revenue attribution
Conversions via the API land on the campaign, the journey and the ad click that started the conversation, and are reported back to Meta's Conversions API with a delivery log.
Ad spend, cost per lead
Record spend by hand or import it. Cost per lead and revenue by ad, beside conversations per ad.
Conversations, team, pipeline, growth
Volume by day and hour, business- versus user-initiated, reply cost after October 2026, response and resolution times, ratings per agent, stage by stage.
Reports and export
A daily or weekly summary emailed to whoever should see it. Any view to CSV or Excel. Your data is never held hostage.
Inbox copilot, summaries, intent
Suggested replies from the conversation and your knowledge base. A summary on every hand-over. Intent detected for a badge and a filter. Translation both ways.
Writers, and answers from your text
Whole templates drafted with Meta's category rules in mind. A described bot becomes a flow. Paste policies and FAQs; the bot answers and hands over when unsure.
Metered, and yours to switch
Insights written from your numbers. Bring your own Anthropic, OpenAI or compatible key, or use credits with a visible balance. Each AI feature is its own switch.
Questions about analytics, return on spend and ai
Can I export WhatsApp analytics?
Yes. Every table and report exports to CSV or Excel, and a daily or weekly summary can be emailed to a list of recipients. No plan withholds export.
How is revenue attributed to a WhatsApp campaign?
Your store or CRM posts a conversion with the customer's number and value to the conversions endpoint. The product matches it to the last campaign the person received within the attribution window, to the journey they were in, and to the Click-to-WhatsApp ad that started the conversation, then reports it to Meta's Conversions API so the ad can optimise.
Which AI models does it use?
Your choice. Connect your own Anthropic, OpenAI or OpenAI-compatible key, or use platform credits with a visible balance. The provider in use is shown in settings, and each AI feature (summaries, suggested replies, translation, intent, template writer, flow generator, insights, feedback scoring, FAQ bot) is its own switch.
Does the AI read my customers' messages?
Only for a feature you switch on, and only the conversation that feature needs. Nothing is sent to a model by default, and conversation text is never used to train models.
Talk to us.
In a forty-minute call we go through what you send today, what it costs you, and what a flagged number would cost you. Then we set up a workspace on your own Meta app and build the first campaign with you.