[No QA] Docs updates for E/A#96773 Agent rule change log in #admins room

[MelvinBot]

Explanation of Change

Documents a user-visible behavior added in #96773: whenever an Agent rule is added, updated, or deleted, Expensify now records a system message in the workspace's #admins room as an audit trail (add/update show the rule title and prompt; delete shows the title).

The existing Create Agent Rules article covers creating, writing, and deleting Agent rules but didn't mention that these changes are now logged in the #admins room, so this adds a task-based section (## How to review Agent rule changes in the #admins room) to that article. Content follows HELP_AUTHORING_GUIDELINES.md, HELPSITE_NAMING_CONVENTIONS.md, and TEMPLATE.md, and reuses the existing UI terminology (Agent rules, RuleBot, #admins room) already established in the article and in the Expensify Chat Rooms for Admins article.

Fixed Issues

$ https://github.com/Expensify/Expensify/issues/660979
PROPOSAL:

Tests

Documentation-only change (no code/UI changes).

1. Preview docs/articles/new-expensify/ai-agents/Create-Agent-Rules.md and confirm the new ## How to review Agent rule changes in the #admins room section renders correctly.
2. Confirm the relative link to the #admins room article resolves.
3. Confirm the content accurately reflects the behavior shipped in [CP Staging][Payment due @mkhutornyi] Render agent rule change logs in NewDot #admins #96773.

• Verify that no errors appear in the JS console

Offline tests

N/A — documentation-only change.

QA Steps

Same as tests. Documentation-only change; nothing to validate in the app.

• Verify that no errors appear in the JS console

PR Author Checklist

• I linked the correct issue in the ### Fixed Issues section above
• I wrote clear testing steps that cover the changes made in this PR
  • I added steps for local testing in the Tests section
  • I added steps for the expected offline behavior in the Offline steps section
  • I added steps for Staging and/or Production testing in the QA steps section
  • I added steps to cover failure scenarios (i.e. verify an input displays the correct error message if the entered data is not correct)
  • I turned off my network connection and tested it while offline to ensure it matches the expected behavior (i.e. verify the default avatar icon is displayed if app is offline)
  • I tested this PR with a High Traffic account against the staging or production API to ensure there are no regressions (e.g. long loading states that impact usability).
• I included screenshots or videos for tests on all platforms
• I ran the tests on all platforms & verified they passed on:
  • Android: Native
  • Android: mWeb Chrome
  • iOS: Native
  • iOS: mWeb Safari
  • MacOS: Chrome / Safari
• I verified there are no console errors (if there's a console error not related to the PR, report it or open an issue for it to be fixed)
• I followed proper code patterns (see Reviewing the code)
  • I verified that comments were added to code that is not self explanatory
  • I verified that any new or modified comments were clear, correct English, and explained "why" the code was doing something instead of only explaining "what" the code was doing.
  • I verified any copy / text that was added to the app is grammatically correct in English. It adheres to proper capitalization guidelines (note: only the first word of header/labels should be capitalized), and is either coming verbatim from figma or has been approved by marketing (in order to get marketing approval, ask the Bug Zero team member to add the Waiting for copy label to the issue)
• If a new code pattern is added I verified it was agreed to be used by multiple Expensify engineers
• I followed the guidelines as stated in the Review Guidelines
• I tested other components that can be impacted by my changes (i.e. if the PR modifies a shared library or component like Avatar, I verified the components using Avatar are working as expected)
• If a new CSS style is added I verified that:
  • A similar style doesn't already exist
  • The style can't be created with an existing StyleUtils function (i.e. StyleUtils.getBackgroundAndBorderStyle(theme.componentBG))
• If the PR modifies the UI (e.g. new buttons, new UI components, changing the padding/spacing/sizing, moving components, etc) or modifies the form input styles:
  • I verified that all the inputs inside a form are aligned with each other.
  • I added Design label and/or tagged @Expensify/design so the design team can review the changes.
• I added unit tests for any new feature or bug fix in this PR to help automatically prevent regressions in this user flow.
• If the main branch was merged into this PR after a review, I tested again and verified the outcome was still expected according to the Test steps.

---

@yuwenmemon, please review the files changed and confirm they reflect the current behavior. Then post a new comment saying @MelvinBot mark this PR as ready for review.

[OSBotify]

A preview of your ExpensifyHelp changes have been deployed to https://c5ae3b1c.helpdot.pages.dev ⚡️

Updated articles:

• articles/new-expensify/ai-agents/Create-Agent-Rules

[melvin-bot]

Concierge reviewer checklist:

• I have verified the accuracy of the article
  • The article is within a hub that makes sense, and the navigation is correct
  • All processes, screenshots, and examples align with current product behavior.
  • All links within the doc have been verified for correct destination and functionality.
• I have verified the readability of the article
  • The article's language is clear, concise, and free of jargon.
  • The grammar, spelling, and punctuation are correct.
  • The article contains at least one image, or that an image is not necessary
• I have verified the formatting of the article
  • The article has consistent formatting (headings, bullet points, etc.) with other HelpDot articles and that aligns with the HelpDot formatting standards.
  • The article has proper text spacing and breaks for readability.
• I have verified the article has the appropriate tone and style
  • The article's tone is professional, friendly, and suitable for the target audience.
  • The article's tone, terminology, and voice are consistent throughout.
• I have verified the overall quality of the article
  • The article is not missing any information, nor does it contain redundant information.
  • The article fully addresses user needs.
• I have verified that all requested improvements have been addressed

For more detailed instructions on completing this checklist, see How do I review a HelpDot PR as a Concierge Team member?

cc @bfitzexpensify

[melvin-bot]

@bfitzexpensify Please copy/paste the Reviewer Checklist from here into a new comment on this PR and complete it. If you have the K2 extension, you can simply click: [this button]

[github-actions]

Prohibited/vague navigation phrasing: "find the relevant system message" is a vague locate-phrase similar to the prohibited "Find the setting" (HELPSITE_NAMING_CONVENTIONS.md, Prohibited Language). This heading is "How to review Agent rule changes," so give explicit, deterministic navigation for opening the room instead — e.g. reference the exact navigation to reach the #admins room (per the Navigation Instruction Standards) and describe the exact system message the reader is looking for.

[github-actions]

Terminology consistency: Use the exact role term "Workspace Admins" rather than the informal "admins" (and "admin team" on the sentence below). HELPSITE_NAMING_CONVENTIONS.md (Deterministic Writing) and the article's own usage of Workspace Admins call for consistent, exact role terminology.

[github-actions]

HelpDot Documentation Review

Overall Assessment

This PR adds a single, focused task-based section (## How to review Agent rule changes in the #admins room) to the existing Create Agent Rules article, documenting the new #admins room audit trail behavior shipped in #96773. The addition is small, well-scoped, and integrates cleanly with the existing article without expanding it beyond its single workflow.

Scores Summary

• Readability: 9/10 - Clear, concise, scannable. The bulleted breakdown of added/updated/deleted messages reads well and the explanatory sentences flow naturally.
• AI Readiness: 9/10 - Heading is a full How to... task-based phrase using the exact feature name, uses only ## under the single title heading, and matches real search intent. No frontmatter change was needed since the added content falls within the article's existing internalScope.
• Style Compliance: 9/10 - Uses exact UI terminology (#admins room, Agent rules, RuleBot, Workspace Admins) consistent with the article and the linked Chat Rooms for Admins article. Bold formatting applied correctly; single relative cross-link with descriptive anchor text placed in an explanatory sentence (not inside steps), per Cross-Linking Standards.

Key Findings

• The new heading follows the Section 2 task-based rule and is placed before the exempt FAQ heading, so heading hierarchy remains valid (one title heading, task-based ## sections only).
• Terminology and casing match both the parent article and the cross-linked article, avoiding synonym drift.
• Cross-link is relative, singular, and descriptive, compliant with link volume and anchor-text rules.
• Minor: the bullet list uses a leading space before the dashes, a small markdown inconsistency; it renders correctly but consider normalizing to standard list indentation.

Recommendations

• Optional: normalize the bullet-list indentation (remove the leading space before the dashes) for markdown consistency.
• No blocking issues. Content accurately reflects the shipped behavior and follows governance guidelines.

Files Reviewed

• docs/articles/new-expensify/ai-agents/Create-Agent-Rules.md - Approved; clean, compliant addition of one task-based section.

Note: Detailed line-by-line feedback has been provided as inline comments.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 292a4d0305

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Qualify the claim that change logs always show a title

When server-side title generation fails, these messages do not show a rule title: AgentRuleChangeLogUtils.ts explicitly treats the generated title as best-effort, add/update fall back to prompt-only messages, and delete falls back to the generic “removed an agent rule.” Documenting titles as unconditional therefore gives admins an inaccurate expectation for this supported scenario; clarify that the title appears only when available.

Useful? React with 👍 / 👎.