Follow up on WhatsApp after the customer has gone quiet
Two or three companies' docs show a full fit.
What counts as done
The agent knows whether the 24-hour window is open before sending; outside it, an approved template with the right parameters is sent and its delivered status returned, and a free-text send is refused with a reason instead of being accepted and failing later.
How agents ask for it: remind the lead tomorrow on WhatsApp
, follow up in three days
, message customers who haven't replied
Does the job 2
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| Linq BB Linq App Inc. | Linq's WhatsApp API refuses a free-text send outside the window with 422 error 2036, nothing sent, and context.expires_at tells the agent when it lapsed; templates are registered and sent outside the window. source |
| Prelude B DING SAS | A reply outside the 24-hour window is rejected with window_expired, and templates are listed with approval status per country before a template send; delivery arrives by webhook. source |
Does the job, with a limit 12
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| 360dialog WhatsApp API + MCP D 360dialog GmbH | The Inbox API exposes messaging_window_expires_at and refuses an out-of-window free-text send with 453. But a wrong template name still returns 202 and fails later with 132001, and the Inbox needs the Premium plan. source |
| AWS End User Messaging BB Amazon Web Services, Inc. | The Social Messaging API reads template status and quality and rejection feedback, but the docs index shows no window field or synchronous out-of-window refusal; Meta's failure comes back as an event. source |
| Bird API + MCP A Bird B.V. | A service message into a closed window is refused with 422 E15044 before anything is charged, and templates send with parameters. Bird says the check is best effort and fails open, so a 202 doesn't prove the window was open. source |
| Kudosity B Known Pty Ltd | Every WhatsApp send is an approved template, and GET /v2/whatsapp/templates filters by status (APPROVED, PAUSED, REJECTED and others). The API never sends free text, so the window question doesn't arise, but no window field or template status webhook was found. source |
| Plivo API B Plivo Inc. | Templates are created, synced and their status shown, with up to 24 hours for Meta approval, and template sends are documented. No window field or synchronous out-of-window refusal was found. source |
| Sinch Messaging APIs + MCP B Sinch AB (publ) | Templates are managed and sent outside the 24-hour window through the Conversation API, but no window field or synchronous refusal was found. source |
| Telnyx API + MCP BB Telnyx LLC | Templates are managed by API and error 40008 names a pending, rejected, paused or disabled template; the docs state the 24-hour rule but no window field or synchronous refusal of out-of-window text. source |
| Twilio API + MCP A Twilio Inc. | Approved templates send through the Content API, but out-of-window free text is accepted and fails afterwards, as acc-24 found running a WhatsApp sales agent; no window field was found. source |
| Vonage Messages API + MCP B Vonage Holdings Corp. | WhatsApp templates send through the Messages API, but an out-of-window rejection arrives by status webhook after a 202; no window field was found. source |
| Wati D Clare.AI Limited | Templates are listed by API and a templateReviewed webhook reports status changes. Free text goes only to an active conversation, but the failure is reported by the Session Message Failed webhook rather than refused in the call. source |
| WhatsApp Business Platform (Cloud API) B Meta Platforms, Inc. | Templates and message_template_status_update webhooks exist, but out-of-window text is accepted and fails later with 131047 (acc-33, acc-34), and approved templates can still fail with 132001 or permission errors (acc-38, acc-39). source |
| YCloud B YCloud International Pte. Ltd. | Templates list by status (PENDING, APPROVED, PAUSED, REJECTED and more) with reviewed, quality and category webhooks. No window field was found, and the Messenger reference says YCloud does not precheck the messaging window. source |
Couldn't check 2
The docs were closed to us, or silent. These carry no mark either way.
| Listing | Why |
|---|---|
| Infobip API + MCP BB Infobip Ltd | WhatsApp templates send through the Messages API, but whether Infobip exposes the window or refuses out-of-window text synchronously wasn't found in the pages that render without script. |
| Photon C Something Great Inc. | The WhatsApp kit sends typed templates, but whether it exposes the window or refuses out-of-window text synchronously wasn't in the pages read. |
Doesn't do this job 4
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Bandwidth Messaging API + MCP BB Bandwidth Inc. | No WhatsApp channel; SMS, MMS and RCS only. source |
| ClickSend SMS API + MCP D ClickSend Pty Ltd | No WhatsApp channel in the API reference. source |
| Sendblue B Round One, Inc. | No WhatsApp channel; iMessage, SMS, MMS and RCS only. source |
| Telegram Bot API D Telegram Messenger Inc. | Telegram only; no WhatsApp. source |
What stops agents finishing
- free text outside the window is accepted then fails by webhook (131047)
- templates rejected, paused or categorised as marketing without warning
- template listed as APPROVED but send returns 132001 or a permission error
Around it
Before: messaging.two-way-customer-agent. After: messaging.confirm-delivery, crm.log-activity.
Where this comes from
Weight 10 of 100 in Messaging APIs: 10 of 69 accounts; nine of ten from 2026, mostly GitHub issues from agent projects whose follow-ups silently failed with 131047
The same as data: /api/v1/use-cases/messaging.whatsapp-follow-up-after-window.json, or the MCP tool get_use_case with id messaging.whatsapp-follow-up-after-window. Other jobs in this category: /api/v1/niches?category=messaging.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.