> For the complete documentation index, see [llms.txt](https://docs.icustomer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.icustomer.ai/pulse/daily-digest.md).

# Daily digest

One envelope a day: what the system did, what needs you, and what is ahead.

The digest is the daily account of the loop: one envelope, once a day, covering what the system did, what already reached you, and what is coming. It is part of Pulse, not a separate surface, the same record, rolled up.

## What is in it

* **What ran**: the plays, activations, and notable decisions of the day.
* **What reached you already**: anything that pulsed earlier appears marked "already alerted," so the digest never double-pings you.
* **What is worth knowing**: inform-mode pulses, the interesting-but-not-urgent, live here rather than interrupting you.
* **What is ahead**: scheduled runs and checkpoints approaching.

## The discipline behind it

The digest exists so interruptions can be rare. Only the urgent tier stands alone in email or Slack; everything else waits for the envelope. If your day was quiet, the digest is short, it reports what happened, it does not perform activity.

## It talks back

The digest is a door into chat: reply to any line, "why did this play pause?", "expand on the audience shift", and you are in a conversation with iHarness with that item's context loaded.

Delivery, when and where the envelope arrives, is configured per user; see [Delivery](/pulse/delivery.md).


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.icustomer.ai/pulse/daily-digest.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
