> For the complete documentation index, see [llms.txt](https://docs.ilert.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ilert.com/incidents-and-status-pages/status-updates/ai-status-update-generation.md). # AI status update generation Let ilert AI draft the message of a status update, and guess which services it should name. Writing to customers is the part of an incident that gets postponed, because it is the part that needs a calm sentence and you are not calm. ilert AI takes a few words and turns them into a publishable [status update](/incidents-and-status-pages/status-updates.md), then guesses which services it concerns and at what impact level. You are still the one who publishes it. Read what it wrote. {% embed url="" %} ## The first update In the [Post status update](/incidents-and-status-pages/status-updates.md#post-an-update) dialog, type a short description of what is happening into the field and click the :magic\_wand: icon beside it. Something like *spacex services unavailable* is enough. ilert AI writes the message and pre-selects the services it believes are affected, each with an impact level.

ilert AI expanding a short phrase into a full status update message and selecting the affected services. — A handful of words in, a publishable message and a service list out.

## Follow-up updates Once an incident has posted its first update, the AI moves to the **Message** field, where it drafts the next update in the context of the ones before it — so a *Monitoring* update reads as a continuation rather than starting the story again.

ilert AI drafting a follow-up status update message for an incident that already has updates. — Follow-ups are drafted against what has already been said.

## What is sent to the model Enough to write the sentence, and no more. **For a first update:** * the **service names** of a small selection of services, chosen by their relation to your prompt and to you — services owned by your teams, for instance. No other service data leaves ilert. * the **summary you typed**, as the prompt. **For a follow-up:** * the service names of the services already on the incident. Services that are not on it are not sent. * the incident's current status. * the message you typed, as the prompt. Not sent, in either case: your alerts, your timeline, your responders, your customers, or anything about services other than their names. {% hint style="info" %} Status update generation uses an external model. It can be turned off account-wide, along with every other external-LLM feature, in [account settings](/ai-and-agents/introduction.md#model-endpoints-and-data-residency). {% 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, and the optional `goal` query parameter: ``` GET https://docs.ilert.com/incidents-and-status-pages/status-updates/ai-status-update-generation.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.