Recently active topics

How are we improving the Assistant’s behavior?Previously, an initial answer could appear complete while the Assistant was still working and additional results were pending. This update identifies when the Assistant is still working through its reasoning and tags messages as updates rather than individual net-new messages with feedback buttons.

Moveworks currently does not support reading images/screenshots. Hence colleagues have to describe the issues in words rather than just sharing the screenshot of error received.

Admins can open Moveworks directly from ServiceNow EmployeeWorks without signing in again or configuring separate SSO on the Moveworks side.

1. Business Context & Compliance RequirementsUnder South Korea’s Personal Information Protection Act (PIPA), administrators who process personal information (PI) must have their active sessions automatically terminated after a maximum of 2 hours of inactivity/active access to prevent unauthorized access.Currently, we configure session limits through our IdP (Okta). However, while Okta handles initial authentication timeouts, active administrative sessions (such as Super Admin or Setup Admin) inside Moveworks remain accessible as long as the browser tab remains open.Because PIPA mandates application-level session invalidation for administrative consoles with access to PI, relying solely on IdP-level policies does not fully satisfy Korean regulatory requirements.2. Request DetailsTo ensure continuous compliance and satisfy regulatory standards, we request the following: Native Role-Based Session Timeout: The ability to configure a maximum session lifetime (specifically 2 hours or cus

As we have a Native CSAT functionality, Can we have get same functionality for NPS as well.Because making changes in Native CSAT is not possible.

SummaryAdd an optional input to the built-in user lookup actions (mw.get_user_by_email and mw.batch_get_users_by_email) so the caller can state up front which user attributes they want. The action should retrieve and return only those attributes. Today both actions return the full user object, including custom attributes, and the only option is to filter the result after the full payload is already in memory. That is too late to prevent the memory and size problems.ProblemThe full user object is large, and the combined payload from batch lookups is approaching the 4 MB limit. If a plugin’s return payload exceeds 4 MB of memory, the plugin can stop working. There have been a few instances where the 4 MB limit was hit and caused a failure.The largest known common payload is 3.6 MB. Compound actions have reached 3.8 MB. Every new ingestion point added to the user object pushes these numbers higher.If the payload keeps growing, other plugins that depend on user objects could fail entirely.

How are we improving the product?We’re expanding access to in-bot alerts so designated recipients can receive notifications through the Moveworks Slack bot, helping teams become aware of issues without regularly checking the Alerts page.Super Admins can manage who receives notifications through Notification Settings on the Alerts page in Moveworks Setup.

It would be great to be able to test impersonating other users as a Moveworks Admin across the AI Assistant. As the assistant steers questions based on attributes from each users, it’s tough to see how pages are returned to employees. It gets even harder when we (IT) have restricted internal runbook documentation vs employee facing documentation, and seeing the differences between what we would get back vs employeees. 

We would like to request the ability for custom Agent Studio plugins to dynamically search and retrieve relevant content that has already been indexed by Moveworks.To clarify our use case, we are not requesting real-time Web search functionality such as Live Search, nor are we looking to use the built-in Enterprise Search plugin directly.Our specific use case is as follows: We have internal knowledge sources already configured and indexed in Moveworks, including: Manuals stored in Box Knowledge articles stored in ServiceNow A user submits a query to a custom Agent Studio plugin. Based on the user's query, we would like the custom plugin to dynamically search the content already indexed by Moveworks and retrieve the most relevant internal knowledge. We would then like to provide the retrieved content as context to an LLM Action, such as generate_text_action or generate_structured_value_action, so that the LLM can generate a response based on the relevant internal knowledge. Ide

Both insights are found in Plugin Insights and there is no way to extract a report from both blocks other than clicking on the total interactions from each content item/topic which is inefficient and having worked on an Interaction report csv to delimit/separate content items by a comma will separate a word from a title even if said title has quotation marks. For those unable to get Data API running, a widget to download a report from content items and topics will prove helpful for those drafting periodic reports.

We believe it would be beneficial to isolate individual connectors so that a failure in one does not cause a full breakdown of user ingestion. For example, recently our Okta connector (used only for proactive account unlock) experienced a failure, and this halted all user ingestion, which is primarily done through our ServiceNow connector. Ideally, an Okta failure would not prevent all user ingestion from happening. This prevented all new hires from being ingested and also caused user attributes that had been updated in ServiceNow not to be updated in Moveworks. 

SummaryEnable users to apply filters in EmployeeWorks Enterprise Search before initiating a search, rather than requiring an initial search before filters become available.Current ExperienceToday users must first enter and execute a search before they can access filters to narrow the results. For users who already know the scope or type of content they want, this creates an unnecessary step and consumes an additional assist before they can perform the search they actually intended.Requested ExperienceAllow users to configure available filters before executing a search.The desired flow would be: Open Enterprise Search Select the desired filters Enter the search query Search within the selected scope Receive relevant, filtered results immediately Users should still have the option to search without applying filters first.ExampleIf a user knows they only want results from a specific source or content type, they should be able to select that filter first and then search, rather tha

Add a method to verify a connector connectivity quickly through the inclusion of a button on the connector config pages. This would be useful for verification after cycling credentials or as a general troubleshooting tool. If it could be integrated where a new credential could be tested before implementation, that would be even better.

SummaryAdd an automated flag or alert when content being ingested (files, sites, and other sources) may contain PII or PHI.BackgroundEach ingestion is reviewed with the requesting teams. However, ingestion requests can include thousands of files, and manual review at that scale always carries some risk that sensitive content goes unnoticed.Proposed CapabilityA detection safeguard that complements the existing review process rather than replacing it. Possible implementations include:A warning at ingestion time when potential PII/PHI is detected A report of flagged files for review before content is made available A configurable detection setting (for example, enable/disable or adjustable sensitivity)ValueAdds a safety net at scale, reducing the chance that sensitive content is ingested unnoticed Supports existing review workflows and strengthens data protection posture Reduces the risk of missed sensitive content by highlighting potential PII/PHI for reviewers, while human review remain

Hi all.I think that some gamification of Moveworks could help increase usage and improve the business value of the platform. A simple points and leaderboard/award system would give organizations a simple way to promote and recognize usage without constantly pushing for agent usage through announcements. Users could earn points for engaging with the bot and earn recognitions or rewards from the business. Currently, the only way to implement something like this would be a custom hacky solution with SharePoint, or another third-party vendor that offers this for Teams. Both options would present technical challenges and limitations for Moveworks usage itself.I would love to hear some other opinions on this! :)