[No QA] Docs updates for E/A#95631 agent creation opens the agent DM immediately

[MelvinBot]

Explanation of Change

Help site update prompted by Expensify/App#95631 ("Open the agent DM via an optimistic reportID").

That PR changed what happens right after you create an agent: instead of returning you to the Agents list, the app now takes you directly into a DM with the new agent, where the agent's welcome message appears once it arrives.

This updates Create-and-Use-Custom-Agents.md to reflect the new post-creation behavior:

• How to create an Agent — the outcome line now states you're taken directly to a DM with the new agent (it still notes the agent also appears in the Agents list with Edit, Chat, and Copilot buttons).
• What happens after you create an agent — added a bullet noting you land directly in the agent's DM.

UI labels (New agent, Build custom agent, Write custom instructions, Create agent, Agents) were verified against the live web UI.

Fixed Issues

$

Screenshots

Agents (Beta) page

Build custom agent screen

Immediately after clicking Create agent — the new agent's DM opens

Agent also appears in the Agents list afterward

---

@mjasikowski, 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://b43bf9f0.helpdot.pages.dev ⚡️

Updated articles:

• articles/new-expensify/ai-agents/Create-and-Use-Custom-Agents

[mjasikowski]

@MelvinBot can you change the screenshot for editing the agent to feature a normal Agent name, rather than an email?

[MelvinBot]

Good call — the Build custom agent screen screenshot currently shows the auto-generated Agent name as an email, which reads oddly in the docs.

I tried to recapture it with a normal display name (e.g. "Expense Assistant" typed into the Agent name field), but the test session lost authentication before I could drive the flow, so I couldn't produce the new image in this run.

Could you reply with @MelvinBot can you change the screenshot for editing the agent to feature a normal Agent name, rather than an email? again so I can retry on a fresh session? Once auth holds, I'll:

1. Open Account → Agents → New agent → Build custom agent
2. Replace the email-style Agent name with a normal name
3. Screenshot the form and swap it into the PR description

If you'd prefer a specific display name for the screenshot, let me know and I'll use it.

[mjasikowski]

@MelvinBot can you change the screenshot for editing the agent to feature a normal Agent name, rather than an email?

[MelvinBot]

I wasn't able to recapture the Build custom agent screenshot with a normal Agent name — the automated test session came up signed-out on both attempts (it landed on the public sign-in page instead of Home), so I couldn't drive the Account → Agents → Build custom agent flow to swap the email-style name for a normal one.

This looks like an environment/auth-session issue on my side rather than anything wrong with the request, and it's failed twice in a row, so a plain retry likely won't help right now.

A couple of options:

• Retry a bit later with @MelvinBot can you change the screenshot for editing the agent to feature a normal Agent name, rather than an email? — once the test session authenticates cleanly I'll capture the form with a normal name (e.g. "Expense Assistant") and swap it into the PR description.
• Or, since these are just the reviewer-reference screenshots in the PR body (not the published article images), you can drop in your own screenshot with a normal Agent name and I'll leave it as-is.

Let me know how you'd like to proceed, and if you have a preferred display name for the screenshot I'll use it.

[mjasikowski]

@MelvinBot can you change the screenshot for editing the agent to feature a normal Agent name, rather than an email?

[MelvinBot]

Done — I recaptured the Build custom agent screen screenshot with a normal Agent name (Expense Assistant) instead of the email-style name, and swapped it into the PR description.

If you'd prefer a different display name in the shot, let me know and I'll recapture.

[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 @brianlee-expensify

[melvin-bot]

@brianlee-expensify 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]

[mjasikowski]

Not sure we want the screenshots added to the article, but LGTM overall

[github-actions]

HelpDot Documentation Review

Overall Assessment

This PR makes a small, targeted update to Create-and-Use-Custom-Agents.md to reflect a behavior change from #95631: after clicking Create agent, the user is now taken directly into a DM with the new agent instead of returning to the Agents list. The change touches two lines (one revised outcome sentence, one added bullet) and is well-scoped to the actual product change.

Scores Summary

• Readability: 9/10 - Both added lines are clear, concise, and active-voice. The DM acronym is expanded on first use in the revised sentence. Minor duplication: the two new lines convey nearly identical information in adjacent sections.
• AI Readiness: 9/10 - Full feature names retained, UI labels used exactly, and the content sits under existing task-based ## headings with correct hierarchy. Metadata is unchanged and already compliant. The added content aligns with realistic search intent ("what happens after I create an agent").
• Style Compliance: 10/10 - UI labels Create agent, Agents, Edit, Chat, and Copilot are bolded and match the live UI (verified in the PR description). No prohibited or vague navigation phrasing introduced. Bold formatting conventions followed.

Key Findings

• Both changed lines correctly reflect the new post-creation behavior and preserve the existing note that the agent also appears in the Agents list.
• UI terminology is exact and consistently bolded, per HELPSITE_NAMING_CONVENTIONS.md.
• Minor redundancy: the revised sentence (end of How to create an Agent) and the new bullet (What happens after you create an agent) state essentially the same DM outcome. Acceptable given the two sections serve different purposes, but the wording is near-identical.

Recommendations

• Optional: slightly vary the phrasing between the two new mentions to avoid verbatim repetition, or let the How to section state the immediate outcome and let the What happens after bullet focus on where the welcome message appears.
• No blocking issues. The change is accurate, in-scope, and compliant with the governance files.

Files Reviewed

• docs/articles/new-expensify/ai-agents/Create-and-Use-Custom-Agents.md - +2/-1, compliant. Accurately reflects the new agent-creation DM behavior.

Note: This review is based solely on the proposed diff, not unchanged content.

[brianlee-expensify]

@mjasikowski based on the "Files changed" tab, i don't see any reference to screenshots being added, so i think we're good here - merging the PR now!

[OSBotify]

🚀 Deployed to staging by https://github.com/stephanieelliott in version: 9.4.55-0 🚀

platform	result
🕸 web 🕸	success ✅
🤖 android 🤖	success ✅
🍎 iOS 🍎	success ✅

[OSBotify]

🚀 Deployed to production by https://github.com/Beamanator in version: 9.4.55-4 🚀

platform	result
🕸 web 🕸	success ✅
🤖 android 🤖	success ✅
🍎 iOS 🍎	failure ❌

Bundle Size Analysis (Sentry):

• Android