> 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/~/changes/vPSzQFfkdJCVWGT5AL1m/ilert-ai/generating-postmortems-through-ai.md).
# Using ilert AI for post-mortem creation
## Understanding the alert -> incident transition and what to do after the dust has settled
As a technical issue transitions from an alert into an incident because it has an affect on business services. Its disruption and impact might make it necessary to revisit what happened and which steps can be taken to prevent a similar issue from reocurring in the future. Assume following sample incident that has reached its resolved state.
A simple example incident that has reached the end of its lifecycle in the RESOLVED state
## When the dust settles
As customers have been notified, the root cause identified and a potential fix in place, the dust and hectic has settled arround the incident. Now it is time to sit back and think about what caused the issue in the first place and if/how such thinks can be prevented in the future.
Usually someone in the team responsible for the services that were impacted by the incident will now start working on gathering all information arround the incident and setup a document with all details that is discussed afterwards. This can be quite cumbersome and ilert AI is here to help reduce the time it takes to get started with a proper doc significantly.
### Using ilert AI to generate a postmortem doc
If ilert AI is enabled, you will find the option to generate a postmortem in the detail view of the incident.
This will open a popup that offers multiple options to fine tune your postmortem document generation.
### By default (no selections)
By default the generation will take all available context of the incident into acccount, such as history updates, subscribers, services and involved users / responders.
### Include alerts
If an alert is linked to the incident, the alerts details will also be taken into account, as well as its timeline. This can help to significantly improve the generation of technical related action items in the final document. You can also link alerts afterwards, as long as they are not resolved yet.
### Including alert related Slack or MS teams channels
When an alert is linked that has an attached **#warroom** Slack channel or MS teams channel the channel will also appear in the selection options of the popup. Channels that are included will be scanned and parsed by the connected ilert Slack or MS teams bot and relevant messages will be included automatically in content of the final document.
It is also possible to paste a chat transcript from any other source manually, this script may contain timestamps and usernames in any raw format, ilert AI will automatically parse and handle the content accordingly.
### Optional fine tuning
You have three additional fields to provide optional content for fine tuning of the postmortem document. The content here has a little higher weight in such that during the generation it can help shape action items or root cause. This is helpful if certain action items or root cause information are already known at the time of postmortem generation and you wish to include them.
## Postmortem creation
When you satisifed with the post mortem input you can click on **Generate post mortem** to enqueue your postmortem creation. As certain sources are pulled, paginated, read and parsed during the creation process it has been decoupled and can take a little moment.
As soon as your document is ready, the status will transition to created.
You may now click on View generated content to see a simplified markdown rendered version of the generated conten:
For our sample alert the generated markdown version looks like this:
At the bottom right you will find the **Open** option which will contain a link to the raw textfile document of your generated postmortem. You will probably want to move this raw version of the document into a shared MS Word or Google Doc for further manual fine tuning and adjustments before sharing it with colleagues.
## Publishing a postmortem
As soon as you are ready to share your document with internal or external stakeholders and subscribers you have the option to link your document to an incident.
{% hint style="success" %}
You may also choose to include your postmortem on all status pages that this incident appears on.
{% 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/~/changes/vPSzQFfkdJCVWGT5AL1m/ilert-ai/generating-postmortems-through-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.