WhatsApp Chat Analyzer: Unanswered Chats & Response Time
Pricing
from $10.00 / 1,000 conversation analyses
WhatsApp Chat Analyzer: Unanswered Chats & Response Time
Analyze WhatsApp Business chat exports you own: response times, unanswered chats, cold leads to follow up, buying intent and repeated questions. Privacy-first: pseudonymous output, no AI API, never connects to WhatsApp or sends messages.
Pricing
from $10.00 / 1,000 conversation analyses
Rating
0.0
(0)
Developer
PRIVATEX
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
5 days ago
Last modified
Categories
Security
Limited permissionsShare
WhatsApp Conversation Intelligence
Find out which customers are waiting, which leads went cold and what everybody keeps asking – from WhatsApp Business chats that your business owns.
You export chats (or send structured messages from your CRM / Cloud API logs); the Actor returns response-time metrics, a prioritised action list and a weekly report. It never connects to WhatsApp and never sends a message.
Who is it for
Small businesses and sales or support teams that handle customers on WhatsApp Business and want to see unanswered chats, slow replies and cold leads without connecting any tool to WhatsApp.
Quick start
- Press Start with the pre-ticked Demo mode: you get a full report on fabricated conversations. Every row is labelled
SYNTHETIC DEMOand demo runs are never charged. - For your own chats: in the WhatsApp / WhatsApp Business app open a customer chat > Export chat > Without media. Paste the file contents into Chat exports as
[{"name":"customer-1","text":"<contents>"}]. - Fill Names that are YOUR side of the chat with your business name and agent names exactly as they appear in the export (everyone else is the customer).
- Press Start. Your message content is erased from the stored input immediately after it is read.
Example input
{"chatExports": [{ "name": "customer-1", "text": "29/10/2025, 09:16 - Ayse: Merhaba, stokta var mi?\n29/10/2025, 09:30 - My Shop: Evet var." }],"businessSenders": ["My Shop"],"timezoneOffsetMinutes": 180}
Example output row (SAMPLE - synthetic, illustrative values; not from a real account)
{"priority": 5,"conversation": "c_3f9a1b2c4d5e","flags": ["unanswered", "high_buying_intent"],"waitingHours": 6.5,"firstResponseMinutes": 14,"intents": ["quote_request"],"synthetic": false}
Pricing
$0.01 per conversation analysed, once per conversation (a conversation with no customer message is skipped and not billed). Re-delivery after a retry or restart never bills twice. Demo runs are free.
Pay-per-event. Platform usage (compute, storage) is included in the price - there is no separate Apify usage bill for you. A negligible Actor-start event ($0.00005 per GB of memory, minimum one) also applies. You can cap spending with Apify's "Maximum charged results / cost per run" setting; the Actor stops cleanly at your limit.
What is verified, and what is not
- Android (12h/24h, day-first and month-first) and iOS bracket export layouts, Turkish characters and intents (quote, price, order status, complaint, availability, booking, thanks) and WhatsApp system notices are covered by automated tests using synthetic chats. Intent rules cover English, Turkish, Spanish and Portuguese.
- This Actor never connects to a live WhatsApp account and never sends a message. It only analyses text you give it.
- Privacy: customers appear as salted pseudonymous ids; phone numbers, names and message text are not written to the dataset (optional masked snippet is off by default). Export URLs, sender names, the pseudonym salt and all message content are removed from the run's stored INPUT before any parsing.
Limitations
- Erasing the stored INPUT cannot remove copies you hold elsewhere (your API client, saved Tasks, schedules) - do not save chat text in a Task. If a run is interrupted after the input was erased, start a new run with your data.
- Intent and sentiment use deterministic keyword rules (EN/ES/TR/PT), not AI; unusual wording is classified as "other".
- Exports contain what is on one phone; read receipts, voice notes and media are not analysed.
- "Unanswered" means the last message is from the customer and older than your threshold; business hours are not modelled yet.
- Need real-time alerts and assignment? A separate self-hosted engine for the official WhatsApp Business Platform is available (see the repository).
Built by PRIVATEX. Questions or a data-format that does not parse? Open an issue on the Actor page and include the (anonymised) column headers or first lines.
What you get
- First-response time – median, p90, share answered within 5 and 60 minutes, never-answered count.
- Conversations that need action – unanswered, 24-hour customer-service window expired, quote/price asked and then silent, high buying intent, complaints – sorted by priority.
- Repeated customer questions – topics asked in 3+ separate conversations (candidates for a FAQ or a quick-reply).
- Bottlenecks – slowest agents and slowest hours (only with 3+ conversations).
- Weekly report (Markdown), JSON and CSV.
All classification is deterministic (EN/ES/TR/PT keyword rules). No AI API, no per-message cost.
Privacy by default
- Customers appear as pseudonymous ids (salted hash). Phone numbers and names are not in the output.
- Message text is not in the output unless you turn on
includeSnippets, and then it is masked (emails, links, numbers). scrubInputAfterRead(default on) replaces the stored run input with a version without message content.- Only analyse chats of customers who contacted your business, and follow your local data-protection rules. Delete the run to erase everything.
Input
| Field | Meaning |
|---|---|
chatExports | [{"name":"customer-1","text":"<exported .txt>"}] – WhatsApp > chat > Export chat > Without media. |
chatExportUrls | Links to exported .txt files. |
messages | Structured alternative: {conversationId, direction: in/out, ts, text, agent}. |
businessSenders | Names that are your side of the chat (required for exports). |
dateOrder, timezoneOffsetMinutes | Export format helpers. |
unansweredAfterHours, followUpAfterHours | Thresholds. |
demoMode | Fabricated conversations, labelled SYNTHETIC. |
Supported export layouts: Android 12h/24h, iOS [date, time], day-first and month-first dates (auto-detected).
Output
Dataset: one row per conversation (priority, flags, waitingHours, firstResponseMinutes, intents, buyingIntentScore, serviceWindowClosesAt, agents). Key-value store: REPORT_MD, REPORT, conversations.csv.
API example
curl -X POST "https://api.apify.com/v2/acts/YOUR_USER~whatsapp-conversation-intelligence/run-sync-get-dataset-items?token=$APIFY_TOKEN" \-H "Content-Type: application/json" \-d '{"messages":[{"conversationId":"c1","direction":"in","ts":"2026-10-28T09:00:00Z","text":"How much is shipping?"}]}'