Skip to main content

Get Started

The roadmap, product ideas, and product plans are subject to change without notice. These plans may be refined, updated, or revised from time to time, based on customer input and market conditions. The plan described herein is provided solely for information purposes, and is not a commitment, promise, or legal obligation to deliver any material, code, or functionality.

Share your feedback in our Product Ideas Portal

Welcome to the Moveworks Product Ideas Portal!We are committed to listening to and incorporating your feedback to our Moveworks Product Roadmap. What...

    Filter by idea status

    Filter by product

    1171 Ideas

    K
    KaviKnown Participant

    Enable export/download of users who have blocked the assistant to admin1. New

    Add an “Export blocked users” capability in the moveworks setup user ingestion area that allows authorized roles to download a list of users who have blocked the assistant. At the moment we need to raise support ticket to get this extract.

    1
    K
    Forum|Forum|2 months ago
    rraj
    rrajCommunity Manager

    Enterprise Search Plugin Rollout to US Customers6. Delivered

    Upgrade all US customers to the new Enterprise Search plugin. Additional updates can be found below  

    0
    rraj
    Forum|Forum|2 months ago
    rraj
    rrajCommunity Manager

    Enterprise Search Plugin Rollout to EU Customers6. Delivered

    Upgrade all EU customers to the new Enterprise Search plugin. Additional updates can be found below..

    0
    rraj
    Forum|Forum|2 months ago
    A
    AnnaTNew Participant

    Providing link to the the system whenever it is mentioned in the response1. New

    There is no reliable way to ensure that a link will be included in the summarized AI Assistant’s response even if it's present in the available knowledge. We want to figure out how we can more confidently surface links to the users in the provided response so that they can be seamlessly redirected. For example when the bot is guiding users to go to SAP, Concur, Workday, learning platform or any other the link should be embedded into the response so that user don’t need to search for the URL.

    0
    A
    Forum|Forum|2 months ago
    M
    MshaulNew Participant

    Version Control in Agent Studio7.0 Duplicate

    We are very excited about the updated Agent Studio, but there is some concern about the associated risk without version control. For instance, if two MW users were working on the same Agent Studio Plugin/Conversational Flow and there was a mistake, they would not be currently be able to revert versions (at least not from within Agent Studio). 

    1
    D
    Forum|Forum|2 months ago
    G
    glambInspiring

    Request to Increase Secure Listener Rate Limit6. Delivered

    Your documentation notes that Secure Listeners are rate-limited to “up to 5 requests per second.” This is a constraint for our workflows where we need to notify 100+ users concurrently for a single daily use case.Under the current rate limit:While we can delay individual webhook calls from a large batch of triggers, doing so introduces delays in the overall communication and degrades the user experience. We can also attempt to load balance webhook calls using multiple listeners to stay within the limit, but this adds unnecessary complexity to our architecture and maintenance. In many cases, we cannot easily control or predict how many webhooks will be fired within a single second, especially for event-driven workflows that generate bursts of activity.It would be very helpful to significantly increase this rate limit or provide higher-throughput options so we can better support high-volume workflows without additional overhead.

    5
    Kevin Mok
    Forum|Forum|2 months ago
    A
    andrewwhitleyInspiring

    Slot Resolver strategy inference suggestions5. Not Enough Info to Make Decision

    Problems:We do not have much influence over how to get slots to infer (descriptions and the 3 inference options are nice, but are not sufficient in many use cases) Slot Resolver Strategies are very poor with inference when the options to choose are objects with multiple attributes. I can make it work by just outputting the name of the value (list of strings instead of list of objects), but I also have description values for each option object that I want to be considered to assist in choosing the correct option. This approach also means the api calls are made twice for resolver strategies: once in the resolver strategy to get the string list and then again to get the object in the conversational process which is needed for further actions. If a slot is inferred incorrectly, the user can ask for a change, but it doesn’t handle that change very reliably, if at all. Asking for all options of a slot does not always work and if it does, it usually is cut off after around 20.Current Workaround:Use a generate_structured_value_action to take in a description slot (and possibly others like the user) and do the selection This enables me to pass it multiple attributes to use for selection and build out a detailed prompt on how to choose the proper values. I have it also return a confidence score so if it isn’t confident in the choice, I can exit the plugin with information to provide more detail One negative here is that it then lacks the full context of the conversation. I can try and grab the context with a slot, but that does not always work reliably. Use plugin, conversational process, and slot descriptions to try and influence behavior as much as possible for choosing options and displaying options properly, but this does not always work reliably.While this is working well, I want slots themselves to be able to handle this sort of behavior instead of building around the problems.Proposed solutions:For a slot, give us a text box to define the system_prompt and user_input just like the generate_structured_value_action. This should work seamlessly with resolver strategies. The system prompt can define the logic on how to use inputs to choose the proper slot value and when it is necessary to ask the user for an exact value. For slots that are not set to always infer, always output a human readable version of the value selected on the action when it is selected. At any time afterwards, the user may request to change the value. If they do so, the conversational process goes back to the action where the slot is set as required and moves forward from there. Slots set as required in following steps should be reconsidered in this case. If a user asks to see all options of a slot that has a resolver strategy, all options are presented to the user and they are not cut off after ~20. The max I have currently is around 130 options for 1 slot. Most are under 20, but I do have multiple over this. Give the context as another system provided variable that can be leveraged in a conversational process like data and meta_info

    4
    A
    Forum|Forum|2 months ago
    D
    dhorvathCommunity Manager

    Version History4. Future Consideration

    Revert changes made in Agent Studio Assets.

    1
    kyril.remillard
    Forum|Forum|2 months ago
    G
    glambInspiring

    Add "provide link to source" capability when serving knowledge1. New

    We have many processes which Copilot summarizes which is usually presented OK for users. However, we get many requests where users will provide negative feedback to the bot because they ask “provide a link to the source” and the bot fails. Users could click the citation number, then the citation, then View Source, but many want to just ask for the source URL directly to the bot because getting to View Source is not as intuitive as being conversational. If View Source has a hyperlink to the citation, the bot should be able to list URLs cited

    2
    C
    Forum|Forum|2 months ago
    R
    RanjiniNew Participant

    How to enforce file-size limits on file uploads in Moveworks Script Actions?1. New

    Hi team,I’m trying to enforce a 1MB file‑size limit on file uploads captured through a Moveworks slot. I attempted this using a Script Action, but it appears the approach won’t work because:The location field of an uploaded file is not a valid URL that can be fetched. Script Actions run in a sandbox and cannot directly access Moveworks internal file storage. Because of this, the script cannot read the file bytes or calculate file size, so validation never triggers.I wanted to check whether Moveworks currently provides any supported method or API to validate file size before sending the file to a destination system via HTTP Action.Is there an officially recommended pattern or upcoming feature for this?Thanks in advance for any guidance

    3
    Kevin Mok
    Forum|Forum|2 months ago
    K
    KaviKnown Participant

    Enable Conversation ID Mapping for Agent Studio Use Cases4. Future Consideration

    I propose introducing a mechanism to pass the conversation ID to use cases created via Agent Studio. Since most ticket operations in our organization—such as ticket creation and notifications—are planned to be customized using Agent Studio, having the conversation ID available within these use cases would allow accurate mapping between bot interactions and downstream ticket actions. This would significantly improve tracking, reporting, and deflection analytics.

    2
    Ajay Merchia
    Forum|Forum|2 months ago
    D
    dhorvathCommunity Manager

    Fine-grained access control (RBAC)2. On Roadmap

    Let multiple teams build in the same environment, without sharing sensitive connectors or overwriting work What is it: Granular control: grant view / use / edit access on each plugin, connector, action, etc. Folder-based defaults: set team access once; new assets inherit permissions automatically Group-based access: assign permissions to teams (not individuals) to simplify ongoing administration. Key dates:Limited Preview target: April 2026 

    1
    D
    Forum|Forum|2 months ago
    D
    dturner26New Participant

    'Copy response' button similar to ChatGPT and Copilot responses1. New

    Request that Moveworks enhance its product to provide a 'copy response' feature similar to ChatGPT and Copilot to save the user from having the select the response text prior to copying it to the clipboard

    0
    D
    Forum|Forum|2 months ago
    S
    sgrimesNew Participant

    Embedded AI Assistant - Informational Banner1. New

    Hello all, Was wondering if we could get something like shown in these quickly made mockups? Ideally a way to specify additional support options and hours up front. Possible even could be utilized to show FEM outage messages like “X Application is down” to minimize a flood of calls/chats.  Icon Image Main Text (Email to Customer Support)  Secondary Text (Email@email.com)  

    1
    C
    Forum|Forum|2 months ago
    R
    ramapr1New Participant

    Configurable footer messaging in Moveworks popup window1. New

    We would like the flexibility to add customizable text to the footer section of popup window within the Moveworks AI agent. This would apply to popup that opens when users click on Get Help link or when a fillable form is launched inside the agent.This enhancement would allow technical teams to easily display generic or instructional information, such as special notices, disclaimers, or guidance directly to users. Having a configurable footer would reduce the need to modify individual form descriptions, providing a simpler and more scalable way to communicate important information to users when it is most relevant.

    0
    R
    Forum|Forum|2 months ago
    F
    fernyNew Participant

    Excel / xls needs to be ingestable1. New

    As powerful as the Moveworks platform is, not having the ability to ingest excel files is a major hindrance, and quite surprising for an AI platform.

    0
    F
    Forum|Forum|2 months ago
    F
    ffranzwaNew Participant

    Presentation options for user feedback in Agent Studio4. Future Consideration

    Our use case is similar to a CSAT Survey. In Classic Paths, we presented a series of static questions to the user, and they clicked on the appropriate button (Very Satisfied = 5 through Very Dissatisfied=1).We need additional features in order to replicate this functionality in Agent Studio:- “Human in the Loop” Action for Conversational Processes. This Action would always pause the conversational process to solicit an interaction with the user.- More control over how options are presented to the user- Show buttons to user for optionsOur Conversational Process has 7 “input” slots to capture the user feedback that is gathered over the course of the conversation. Each slot is set to “Always prompt user” with the desired question in the slot description and a resolver strategy with the possible responses. The bot still infers the user input since many of the slots have identical text in the resolver strategy. An explicit Action to ask for user input as part of the Conversational Process would be welcomed.We show ‘Very Satisfied’ to the user as the first option. The bot always picks this as ‘Option 1’ and allows users to select this option by pressing 1. Very Satisfied is a 5 and our users are familiar with that value due to how ServiceNow records this information. Asking users to select 1 for Very Satisfied is confusing and I do not see a way of preventing this from being shown to the users. We would like to have control over the presentation for soliciting user input. Along these lines, support for buttons and button labels with emojis would be welcomed.

    2
    Kevin Mok
    Forum|Forum|2 months ago
    J
    João Durand

    Request to Adjust Time Out Thresholds for Compound Actions4. Future Consideration

    Hi Team,We’ve recently started using generation_text_action within Moveworks compound actions, incorporating LLMs with reasoning capabilities—specifically GPT-5.1.During this implementation, we noticed frequent time outs when handling high-reasoning requests and even occasionally with low-reasoning tasks, particularly when large contexts are provided to the LLM.As we embrace these new demands for reasoning models and more complex analyses, we would like to discuss the possibility of increasing the time out thresholds for compound actions. This change would not only enhance the capabilities of reasoning LLMs but would also support listeners that are highly dependent on compound actions. For instance, raising the time out limit would enable us to notify more users (e.g., beyond the current cap of 50) without compromising performance.We believe this adjustment will significantly benefit our workflows, particularly as we adopt more advanced models and use cases.Looking forward to your thoughts! 

    5
    Ajay Merchia
    Forum|Forum|2 months ago
    nicholas.marr
    nicholas.marrNew Participant

    Agent Studio Similar Trigger Phrases Warning4. Future Consideration

    We work in a shared environment with hundreds of developers. It would be helpful if the Conversational Plugin window could give some warning when a similar trigger is being used for another plugin as a sort of heads up to the developer that this use case was already created. 

    3
    Ajay Merchia
    Forum|Forum|2 months ago
    S
    ShailaThoratNew Participant

    Filter reportees based on start date/hire date3. Existing Functionality/Native Skill

    Hi Team,The result of query ‘List all my reportees’, should exclude people with start date/hire date (from workday) is in future. Please refer to conversation from service ticket: Case 00040244 ThanksShaila

    3
    Ajay Merchia
    Forum|Forum|2 months ago
    ajohanson
    ajohansonEmployee

    Automatic plugin re-triggering post UCA re-auth7.0 Duplicate

    Formally submitting product request on behalf of The Wonderful Company: After a user is prompted to re-authorize 3rd party access, ideal experience would be for AI Assistant to automatically re-trigger the initial plugin request. As seen in below screenshot, user experience is not straightforward to know to type ‘retry’ to re-trigger the approve timecard plugin:  Additional details of request here:  

    5
    Ajay Merchia
    Forum|Forum|2 months ago
    J
    João Durand

    Pictures or image files summarization by the assistant4. Future Consideration

    Hi Community,We had a request where for example a person is locked out of their computer - the assistant takes an image and based on the image extract the key of the machine to unblock the computer.The idea would be to be able to include image files, screenshots and pictures taken from Microsoft Teams and moveworks would be able to act - summarize - extract relevant information for the user.Furthermore this would also assist if a user is having a big error message  and he could take a print screen and the assistant would convert this to text  and query the knowledge base.thank you

    2
    Ajay Merchia
    Forum|Forum|2 months ago
    J
    João Durand

    Expanding Moveworks with Additional LLM Providers4. Future Consideration

    Hello Community,Nowadays we’re seeing significant innovation from multiple LLM providers.Would it be possible to expand access beyond Azure OpenAI models to include additional providers such as Anthropic (Claude), Google (Gemini), and others?I believe expanding model options would significantly enhance the platform specially in agent studio use cases - using LLM actions.Would this be something worth considering?

    2
    Ajay Merchia
    Forum|Forum|2 months ago
    J
    jeremy.spearsParticipating Frequently

    AD Groups in Audience Settings4. Future Consideration

    It would be very helpful if the Audience Settings in Plugin Launch Configuration supported targeting users based on Active Directory (AD) groups.Today, targeting relies mainly on Roster data, which can make it difficult to accurately manage specific user groups. This becomes especially challenging when trying to manage small or dynamic audiences.One example is allowing users to opt in as beta or limited preview testers for plugins. Without AD group support, administrators have to manually update audience settings or rely on imperfect roster attributes, which creates ongoing maintenance work.If plugin audiences could reference AD group membership, admins could simply manage access by adding or removing users from the group, making beta programs and staged rollouts much easier to manage.

    3
    Ajay Merchia
    Forum|Forum|2 months ago
    L
    lpedNew Participant

    Unable to identify the field for retrieving CSAT Score (1–5) via the Data API.1. New

    We are looking to retrieve the CSAT score (1–5) submitted by users through the Data API for reporting purposes. However, upon reviewing the available fields in the Data API, we were unable to identify a specific field that captures the numerical CSAT score.We have referred to the available documentation (https://docs.moveworks.com/ai-assistant/analytics-performance/data-api/data-api-release-notes) but were unable to find a clear mapping for this field. Could you please help us identify the correct field that should be used to report on the CSAT score?

    0
    L
    Forum|Forum|2 months ago

    Filter by product

    • All products
    • Analytics
    • AI Assistant
    • Agent Studio
    • Employee Experience Insights
    • Knowledge Studio
    • Moveworks Setup
    • Enterprise Search
    • Content Integrations
    • Content Gateway
    • Other Integrations
    • Next Gen Triage (2.0)
    • MW4Web
    • Service Management
    • AI Agent Marketplace
    • Agentic Reasoning Engine
    • EmployeeWorks
    • General
    Terms & ConditionsAccessibility statement