Build better products with our product team.
I’m sure we’ve all run into this where we have impatient users who have already submitted an Incident regarding an issue and because they didn’t hear back instantly create another Incident, possibly a third, in hopes that it goes to the top of the list and gets addressed instantly.The idea would be that as the user is creating an Incident through the bot, it could read the unresolved Incidents for that user and if what they are asking matches it can either prompt if it’s the same as the Incident that’s currently unresolved and if they click yes then it provides them the ability to update that Incident rather than create a new one, or provide other information to resolve their issue if it’s not the same. Hopefully preventing them from creating multiple Incidents for the same issue.
Is there a plan to ingest SNOW long description? Currently what I understand is MW is using the Form title and its short description to predict which is the right catalogue to provide to end user. However there are times that most of the relative information can be found in the long description. So I’m not sure if there is a plan to allow MW bot to read also the long description and use it to provide the correct form to end user.
When asking the AI bot to set ourselves as some “Head of department”, Bot responds saying it will remember . and when subsequently ask who is the head of the department , it provides us the response as our name.Though this is only for that particular user in Context but this misleads the user in expecting the the information is set somewhere in the backend .Expectation is it must inform , it doesn't have the capability to set something - or point out to some resource where user can do it by themself
Since we turned on ticket interception, I’ve received multiple complaints from end users. While the information the bot provides is helpful and is resolving tickets, we’d like the bot’s additional response to go into Work Notes instead of to the “Additional Comments” section of ServiceNow, which generates extra email traffic to the user.
To support secure and scalable use of Moveworks’ Employee Communications feature across our enterprise, we request the introduction of two distinct roles: Employee Communications Admin and Employee Communications User.The key difference should be that only Admins can send messages to all users. With a workforce of over 390,000 colleagues, unrestricted access poses a substantial risk of accidental or malicious mass messaging.As demand from communications teams grows, we need to onboard more leads—but current limitations force us to use least-privilege access, creating bottlenecks and slowing adoption. Role-based access would allow us to safely expand usage while maintaining necessary controls and governance.
When the bot is on a SharePoint or Support page, the image sometimes blocks content or fields needed by the user. Having the ability to minimize or temporarily close the bot or move it around the screen would help our users with adoption. They are frustrated now.
The CSAT data is helpful, but it would be far more valuable if it were paired with the actual interactions and feedback from the users who submitted it. That way, we can quickly see the reasoning behind their rating or comment. Without this connection, we have to dig into the raw interactions report and manually isolate each user’s conversations—a process that is both time-consuming and inefficient.
Hello,I have been having difficulty trying to combine the return of multiple actions in Agent Studio’s Conversational Process Editor.This could possibly be resolved with a final return object that combines the output of the two objects so they are interpreted by the reasoning agent in a single combined manner instead of it taking liberty in which fields/actions to output.Another solution could be having a static message box instead of content activity where I can directly map out the fields from both of the actions to my custom message that I want consistently outputted.This is for a “People Lookup” plugin which combines mw.get_user_by_email and our own GET_direct_reports_from_servicenow.I have tried extreme prompting to get a more consistent output and have found that by providing an example in the final step, Content Activity, I have received better results but very often the reasoning agent takes liberty in choosing which data to show the user. For mw.get_user_by_email I have,display_instructions: "'If asked Who is this person, your task is to list all specified fields for a user from the {{mw_user}} slot in a bulleted list. Also, always include the direct reports fetched using AS_GET_get_direct_reports_from_servicenow. If a field does not exist or is empty/null for the user, still display the field with a blank value for consistency. Example Output: Here are all available fields for ***** ****: ... Include direct reports such as: - ****** ****** (******.******@***.com) - ... If the user only requests a single field like MyID, respond with just that field, but ensure the direct reports are still fetched concurrently.'"instructions_for_message: "'If the user asks Who is this person, always display the full list of specified user fields including direct reports. If a single field such as MyID is requested, display only that specified field.'"instructions_for_model: "'If the question is Who is this person, show the full user fields and their direct reports. If the question specifies a single field like MyID, return only that field from {{mw_user}}.'"For GET_direct_reports_from_servicenow I have,display_instructions: "'Your task is to list the direct reports found in {direct_reports} for the user stored in the {{mw_user}} slot. If this action is invoked, it should always run as part of the response to ensure complete information is provided. If empty, respond with: No direct reports found.'"instructions_for_message: "'If the user asks for their direct reports, always display the full list of specified direct report fields. If they request Who is this person, show the full user fields including direct reports.'"instructions_for_model: "'If the question is Who is this person, show the full user fields including direct reports; if the request is only for direct reports, list those accordingly.'"For the Content Activity I have,Your task is to always list the full list of the following fields for a user stored in the {{mw_user}} slot when asked "Who is this person?" Also include a list of their direct reports found in {direct_reports}. List the specified fields and their values in a bulleted list.If a field does not exist or is empty/null for the user, still display the field with a blank value for consistency. Do not shorten or summarize the output for the user. Strictly stick to the example output. If the response is shortened or summarized, prompt the user to say, “If you would like to see the full output of fields and direct reports, say Show More.”If the user requests a single field (e.g., MyID), respond only with that field. If the user asks "Who are their direct reports?", only list the direct reports from {direct_reports}.Example Output:Personal Information- Full Name: ***** *******- First Name: *****- Last Name: *******- Email: *****.*******@***.***- Employee ID: ******- Employee Number: *********- SAP Badge Number: ********- MyID: ******- Phone Number: +1 (***) ***-****Role & Department- Role: ******* **********-**** ************ 3- Department: ********** *********- Job Family Group: *** - *********** **********- Business Unit Hierarchy: ********** *********- Division: ***** *********** ****** - *****- Management Level: **- Is Manager: ****- Employee Type: ********Location- Location: **, ******* **** - ** - ****, **-** **- Timezone: **/*******- Entity Code: ****Reporting Structure- Manager Email: ***.*******@***.***Sector & Tags- Sector: *********- User Tags: *****_****Direct Reports- ****** ****** (******.******@***.***)- **** ***** (****.*****@***.***)- ***** ***** (*****.*****@***.***)Before providing an example the reasoning agent would almost always summarize and shorten my example based on its own internal weightings and display instructions for short concise answers. With the example it provides the full output 70-80% of the time but more times then not the Direct Reports state “No direct reports found.” even though when I check the logs I see that GET_direct_reports did successfully pull them.I imagine that these improvements would open the doors for move complicated multi step automations built directly in Agent Studio. Something akin to n8n which provide Split, Merge, Manual Mapping and Structured Output Parser nodes.Thank you for your help!
We are currently encountering response timeout errors when executing Moveworks actions, particularly when calls to external systems take longer than expected. On testing these endpoints with Postman, we observe that responses are received, but sometimes after more than 60 seconds. The inability to configure timeout duration dynamically is causing integration challenges and reliability issues.We propose introducing a feature that allows for a separate configuration file, where timeout values can be easily increased or decreased as needed. This would enable teams to optimize and test timeouts based on the performance of integrated external systems, thereby minimizing timeout errors and improving overall flexibility.Implementing dynamic timeout configuration would help ensure smoother operations for a variety of use cases. Could this feature be considered for future releases?
We are requesting a change to the Creator Studio Connectors page. Currently, there is no option to view the list of use cases connected to each connector. Having this functionality would be helpful, as it would allow us to easily identify which use cases are dependent on specific connectors, without the need to check each use case individually. This change would be helpful for our understanding.Please find attached image.Creator studio Connectors Page
When users ask for the location of a conference room, sometimes the map is shown and sometimes it only appears in the citation. There isn’t any reason why it is shown one way or the other, but the inconsistent UX is confusing and bad experience for our customers. We use OfficeSpace- Can we show all maps in the main window and not in the citations, it is very problematic especially on mobile devices. Example of one being displayed only in citations and the other in bot message
Hi Team,Currently our knowledge managers are finding it difficult to identify which support group they need to coordinate with for the knowledge updates / gaps recommended by knowledge studio.1. Is it possible for Moveworks to include information about the "Support Group" that resolved most incidents associated with recommended knowledge article2. Is it possible to include information about "Support Group" in addition to individual SME name in the individual cards for incident source informationThanks,Milind
Currently, tickets resolved by users in our AI assistant are closed with the note “User selected to resolve issue via bot.”Our various application teams seek a solution that prompts users to specify the actions they took to resolve issues for incident analytics purposes. Users can enter details about how they resolved the issue in open text.
There are times when translating specific HR related program names or fields don’t make sense. For example, recently we deployed job requisition approval notifications. Though this was a targeted audience use case, it was still global so there was opportunity that someone would receive the notification in a non-English language. The Job Requisition titles were translated, however our translation reviewers commented that it would be preferred to keep in English because the translated versions of JR titles don’t always reflect appropriately and it would be less confusing to keep in English. I noticed that there was an older idea regarding company jargon not translated, but sometimes think it should be expanded to also be functional jargon.
It would be nice if we could add a label to the various items in the Conversational Process.As you see in my example below, it can get confusing in complex conversations, when the same item is chosen multiple times:
The Wonderful Company is using recurring Moveworks Campaigns to collect ongoing feedback from employee groups. The in-chat button responses work great and make participation easy.But when it comes to reviewing the data, the experience is very inefficient. Each day's or week's responses are buried at the bottom of the campaign view, and there’s no option to "Download All" while the campaign is still active. That button only appears once the campaign is canceled, which defeats the purpose of running a recurring campaign.Is there a better way to access or export this information without stopping the campaign?
Create separate instances or folders within Creator Studio (Agent Studio) where access can be restricted by developer or team. Specifically, if we can define which developers have permissions to a particular instance or domain, and restrict their access from other instances or folders—including any associated plugins, events, queries, and paths.
Could you add in Open AI Communities data into the external answers? - Introducing GPT-5 - Resource | OpenAI Academy
Can we have additional Data APIs to expose master data - Knowledge and Forms.
Using Agent Studio, is there a way to collect a optional comment when a approver is approving or denying something? This can be passed to the initiator or stored in the source system.
Azure ACS will stop working for new tenants as of November 1st, 2024 and it will stop working for existing tenants and will be fully retired as of April 2nd, 2026.Would like to change to use Graph Delegated (specific user access very limited) permissions instead of Application level (full tenant access) for SPO ingestion. https://learn.microsoft.com/en-us/sharepoint/dev/sp-add-ins/retirement-announcement-for-azure-acs
Already have an account? Login
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.