Build better products with our product team.
Occasionally, some unexpected behavior will arise from an Agent Studio plugin, built in functionality, etc. Today I was picking through the logs for a plugin that ran earlier this week and found which log identified the break, but it’s not expected to me based on previous testing. I prepared to open a support ticket and thought: It would be nice to have a quick/deep link of some sort to open a ticket directly from this log entry I’m viewing, with the log automatically attached to the support ticket.The same functionality could be useful on the Raw Interactions table in the Analytics module as well.
New Max Capacity connector for MS Teams - this will enable searching over all of you conversations from within MS Teams. This will be a live search connector.
What’s changing?Moveworks is introducing a dedicated Content experience in the Troubleshooting Hub within Moveworks Setup. It will bring content health, record-level troubleshooting, and access investigation into one customer-facing experience.The Troubleshooting Hub will help admins and implementation partners understand whether content and permissions are syncing correctly, identify customer impact, and resolve issues without navigating multiple tools or interpreting internal ingestion processes.The experience will include:Content health at a glance: Review synced and failed record counts across the organization and individual content sources.Source-level monitoring: Understand whether a newly configured source is scheduled, progressing normally, active, or affected by an issue.Impact-based issues: See clear explanations of problems such as blocked first syncs, stopped updates, stale permissions, or unavailable content.Record-level troubleshooting: Search content and understand whether each record is synced, stale, or failed, including the relevant reason and freshness information.Check Access: Test whether a specific employee can access a specific record and understand the identity, group, permission, audience, and access-rule decisions behind the result.Guided resolution: Review the affected scope, likely cause, recommended actions, ownership, and the checks needed to confirm recovery.These changes are designed to help admins and partners detect content and access issues earlier, understand their impact, and resolve common problems with less reliance on Moveworks Support.
Making the Slack app available via the Slack Marketplace Store, for customers on the US Data Center
Use the Slack pop-up to manage the MW Reference modal and Global Actions
Today, any change to a user’s email address—the universal join key in our instance—causes Moveworks to create a new user record and deactivate the previous one. This breaks analytics continuity, as historical interactions remain tied to the old user ID and metrics such as first_interaction_time and latest_interaction_time reset under the new record. This behavior can also be triggered when a user updates their first or last name in Entra, since those updates often result in an email address change.Proposed solution: Introduce a stable, canonical user identity that is independent of mutable attributes like email address and use that identity to preserve analytics continuity across profile changes.
We'd like the ability to filter Unily content ingestion by page/content type.Currently, all content types are ingested without the option to exclude specific categories. This creates a practical problem: content types like news articles have a short shelf life and, once stale, can cause the assistant to return inaccurate or outdated responses. The only current option is to exclude entire site sections, which is too blunt when the issue is type-specific.A page type filter — ideally configurable per connector instance in the admin UI — would allow teams to include only the content types that are appropriate for AI assistant retrieval (e.g. policies, how-to guides, FAQs) and exclude those that aren't (e.g. news, announcements, event pages).This would improve response accuracy and give admins more precise control over what the assistant surfaces to users.
Major upgrades to Data Crawling Viewer and Control Center with crawled records view, failed API call insights, record activity logs, improved indexing terminology and Redesigned UI/UX.
Key DatesFrontier: May 18 2026Standard: May 20 2026Basic: May 26 2026Learn more about our model upgrades here.</ul><p><strong>Tool Response Rendering Improvements</strong><br />We've made some updates to how the Moveworks AI Assistant presents tool responses!<br />The Assistant now presents clean and concise results. Previously, some responses were excessively verbose or surfaced extra, unnecessary information, rather than synthesizing it into a helpful answer. Improvements include four changes that will make responses clearer:</p><ul><li><strong>Relevance by default:</strong> When sharing information from a tool response, the Assistant surfaces only details relevant to your request. Raw data fields, internal identifiers, and technical values you can't act on are omitted.</li> <li><strong>Synthesized answers:</strong> When multiple tools contribute to a response, results are combined into a single coherent answer.</li> <li><strong>Plain-language errors:</strong> When a tool encounters an error, the Assistant describes the outcome in plain language.</li> <li><strong>Clean output by default:</strong> The Assistant won't include verbose technical data in responses unless it's directly useful to you.</li></ul><p><strong>To verify the improvements</strong><br />After the update is live in your environment: Ask a question that normally triggers a verbose tool response. The Assistant should return a concise, relevant answer.
Already have an account? Login
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.