> 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/generating-incidents-using-ai.md). # AI status update generation {% embed url="" %} In the heat of incident response, it's essential to keep your focus on resolving the issue at hand. Sometimes, drafting a comprehensive and accurate [status update](/incidents-and-status-pages/status-updates.md) can be challenging, especially under stress. That's where ilert's AI-assisted status update generation comes into play. ## What does ilert's AI-assisted status update generation do? ilert's AI-assisted status update generation is designed to help you write [status updates](/incidents-and-status-pages/status-updates.md) swiftly and accurately. It streamlines the process of documenting what is happening and what is affected, so you can concentrate your efforts on resolving the issue. ilert AI also intelligently guesses which services—along with their impact level—should be included in the update. ## How to use ilert AI for a first status update When you post a status update, provide a very short summary of what you want to communicate in the summary or message field and click on the :magic\_wand: icon on the right of the input field.
Based on the summary (e.g. "spacex services unavailable"), ilert AI will generate the message and also predict and include relevant affected services. ## How to use ilert AI for follow-up status updates In the midst of incident resolution, providing regular updates can be a complex task, especially when the pressure is high. That's where ilert's AI feature steps in to assist you. Just as it helps with a first status update, ilert AI can also efficiently produce follow-up updates for an ongoing incident. Whether you're deeply engaged in the response or merely aiming for a swift closure, ilert AI is there to ensure proper communication about all impacted services.
## What kind of data is shared? For a first status update: * Service **names** for a small selection of services that ilert AI chooses based on the relation to the prompt or the context of the user entering the prompt, e.g. services owned by related teams. No other service data is shared. * The provided **summary** is included in the prompt. For follow-up status updates: * Service names of the services included in the ongoing incident. Service names that are not part of the incident are not shared. * The current status of the incident. * The entered message content is used as the prompt. --- # 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/generating-incidents-using-ai.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.