[ON week] AI-feedback updates to Security AI docs #3935
Merged
+61
−14
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
nastasha-solomon
approved these changes
Nov 14, 2025
Contributor
nastasha-solomon
left a comment
nastasha-solomon
left a comment
There was a problem hiding this comment.
Nice job gathering and applying the feedback!
| This section shows an example workflow for triaging a specific alert. | ||
|
|
||
| **Scenario:** You are investigating an alert: "Multiple Failed Logins Followed by Success - user: jsmith" | ||
|
|
Contributor
There was a problem hiding this comment.
This might be a good place to use the stepper component: https://elastic.github.io/docs-builder/syntax/stepper/
| 3. Click the **Alert summarization** quick prompt. AI Assistant shared an initial alert assessment. | ||
|
|
||
| **Step 2: Assess Criticality and Context** | ||
| Ask AI Assistant: |
Contributor
There was a problem hiding this comment.
Do users need to ask the assistant the following questions in any particular order? Also, do they need to ask all of these questions or just some?
Contributor
Author
There was a problem hiding this comment.
No particular order, just examples of what users might consider asking to get more info.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #3933. This PR is based on Nastasha's and my on week project. We've been using LLMs to conduct user research on our docs. After iterating on our prompt and trying it with severlal LLMs, I opened this PR because I wanted to make some initial updates to the docs in the section I've been focusing on for user research: Security AI docs.
This PR contains a variety of edits intended to fix minor mistakes (redundancy, imprecise language, and unanswered questions.
This PR was created using AI, mostly GPT5 and Claude sonnet 4.5. Some of the text was drafted by AI. All of it was edited by me.