> For the complete documentation index, see [llms.txt](https://docs.perisclaw.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.perisclaw.com/what-perisclaw-can-do/schedule-reminders-and-messages.md).

# Schedule reminders & messages

WhatsApp is where your obligations get made, but it gives you no way to handle them on time. Perisclaw fills that gap two ways — bringing things back when you need them, and sending things exactly when they should land. You set it all up from the chat you're already in, by text or voice note, in the words you'd naturally use.

## Reminders that actually come back

A lot of what happens on WhatsApp needs you *later*, not now — a follow-up due Friday, a bill on the 1st, a call you promised to make after the weekend. Starring a message only bookmarks it; nothing brings it back at the right moment. Perisclaw does.

* **Set a reminder from natural phrasing.** *"Check the proposal at 4 PM,"* *"EOD,"* *"tomorrow morning,"* and *"next Friday"* all resolve to the right time in your timezone — no date to pick.
* **Keep the context attached.** A reminder tied to a conversation comes back with the original message quoted or the chat linked, so you know why you're being pinged.
* **Snooze the way you'd say it.** *"Snooze this until tomorrow morning"* moves it without a second thought.
* **Let it close itself.** If the reminder was to follow up with someone and you've already replied, Perisclaw sees it's done and clears it.

![A reminder from Perisclaw: "Reminder: Call +91 98765 43210 regarding the Q4 headcount. You wanted to finish this before your 3 PM meeting."](/files/KTaMx0Dj6mJIzZof6OEP)

## Messages sent at the right moment

The opposite problem is timing what you *send*. A birthday wish should land at midnight; a status update should go out every Friday at 5. Perisclaw composes it now and delivers it later, so you don't have to be on your phone at that exact moment.

* **Schedule a one-off message** to any chat — written now, sent at the time you choose.
* **Send on a recurring schedule** — like a weekly check-in to a group — without being asked again.

{% stepper %}
{% step %}

### Tell Perisclaw what to send and when

From your [self-chat](/getting-started/using-perisclaw.md) or any chat with `/claw`, describe it plainly: *"send the team a check-in every Monday at 9."*
{% endstep %}

{% step %}

### Confirm the draft

Perisclaw shows you what it'll send and when, so you can tweak the wording or the timing before it's locked in.
{% endstep %}

{% step %}

### It sends at the scheduled time

You'll see it go out — and for recurring messages, it keeps doing so until you ask it to stop.
{% endstep %}
{% endstepper %}

## Things to ask

* *"Remind me to send the invoice on Tuesday."*
* *"Send 'happy birthday' to Maa at midnight."*
* *"Every Friday at 5 PM, send the weekly update reminder to the team group."*

{% hint style="info" %}
Reminders also fold into your daily [digests](/what-perisclaw-can-do/track-commitments-and-tasks.md), so they arrive next to the chats that need you instead of as scattered alerts. For recurring work that needs judgment rather than a fixed message, see [Automated routines](/what-perisclaw-can-do/automated-routines.md).
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.perisclaw.com/what-perisclaw-can-do/schedule-reminders-and-messages.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
