WhatsApp chatbot analytics
Meta reports delivery and template quality. This reports whether your agent answered the customer, from the same Cloud API webhooks.
Meta gives you a lot of numbers about WhatsApp, and every one of them is about the envelope rather than the letter.
What Meta exposes
| Messages | Sent and delivered counts. |
|---|---|
| Templates | Sent, delivered, read, clicked, and the cost of each. |
| Pricing | Volume, cost and tier. Charged per message since July 2025. |
| Quality rating | A reputation score for a template and for a phone number. |
Quality rating is the one with a misleading name. It is computed from recipient reactions, things like blocks and low read rates, and it governs how many messages you may send.
It says nothing about whether your agent was correct. A template can hold high quality while the agent behind it answers badly all week.
Reading the conversation instead
Evidova takes the same Cloud API webhooks Meta already sends you and scores the conversation inside them against rules you approved.
- Whether the agent answered the question that was asked.
- Whether it said it was not a person when asked.
- Whether it invented a price or a delivery date.
- Where the customer stopped replying, and why.
Connect it
Add the Evidova URL as a webhook destination on your WhatsApp app.
Your existing destination keeps receiving everything. We read a copy.
Choose what is stripped before storage.
Phone numbers and other personal details can be removed as the message arrives.
The Cloud API sends audio where a customer sent a voice note, so a score can rest on what was said and not only on what was typed.
Read next
- Quickstart: connect a platform · Ten minutes, one path, from a webhook to your first score.
- Webhook reference · The URL, the signature, and what we answer a delivery with.
- All twelve platforms · Every voice and chat stack Evidova reads, side by side.