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

    1293 Ideas

    andrew.mairena
    andrew.mairenaCommunity Manager

    Slack UX Enhancements4. Future Consideration

    A best-in-class Slack experience — improving usability, increasing trust in assistant responses, and enabling users to complete more work directly within Slack.

    0
    andrew.mairena
    Forum|Forum|1 month ago
    andrew.mairena
    andrew.mairenaCommunity Manager

    Teams Assistant UI Experience Revamp4. Future Consideration

    Modernizing our Teams platform with new UI elements — chat threads, text streaming, and side buttons. 

    0
    andrew.mairena
    Forum|Forum|1 month ago
    KellyMVCommunity Manager

    Specialized Assistant: IT BU ServOps Assistant4. Future Consideration

    Bring a best-in-class conversational experience to IT fulfillers, streamlining service request handling and fulfillment tasks.

    0
    Forum|Forum|1 month ago
    JacekU
    JacekUNew Participant

    Make Question and Answer Config available for users1. New

    There are situations where an unexpected update or an urgent change occurs. In those situations it would be good to be able to create a immediate Question and Answer response available in the system. Creating a knoweldge article and waiting for it to ingest takes too long when an immediate response is required. Sending employee comms is also not always the best approach. It would be best if questions and answers could be setup.As far as I am aware this is an option but it has to be configured by moveworks support, it would be best if it could be easily configurable in the Moveworks settings so client can immediatley make change.

    2
    Forum|Forum|1 month ago
    Don.CocoNew Participant

    Ability to turn off plugin and actions in Agent Studio3. Existing Functionality/Native Skill

    Our company is still getting its feet wet in Agent Studio but one thing that Ive noticed is that there seems to be remnants of old projects or ideas that aren't being used right now. I’d like the ability to turn off inactive actions or plugins instead of just having to delete them. 

    3
    Kevin Mok
    Forum|Forum|1 month ago
    kyril.remillard
    kyril.remillardCommunity Manager

    Assistant Store2. On Roadmap

    Discover and deploy a curated, vetted library with Pre-built Assistants, templates, and more. 

    0
    kyril.remillard
    Forum|Forum|1 month ago
    KellyMVCommunity Manager

    World Knowledge in Enterprise Assistant2. On Roadmap

    Enable Brief Me on Web and Web Search into the Enterprise Assistant as a first-class capability

    0
    Forum|Forum|1 month ago

    Improve Button Interaction Feedback in the Chatbot1. New

    To improve the user experience, action buttons (e.g., Approve, Reject, create) should become disabled (greyed out) after they are clicked.Currently, after a user clicks a button, the bot sends a confirmation message (e.g., "Thank you for approving"), but the button itself remains active. Sometimes This can leave users unsure whether their action was successfully registered and may lead to repeated clicks.Disabling the button after it is selected would provide clear visual feedback, prevent duplicate actions, and create a more intuitive and seamless user experience.

    1
    Forum|Forum|1 month ago
    LAWRM064New Participant

    Expired Link Handling for Employee Communications1. New

    Problem StatementEmployee Communications campaign links (both in-text URLs and button links) currently expire after 14 days. When employees attempt to access an expired link, the experience is unclear and can lead to confusion, failed journeys, support requests, and reduced engagement with important communications.Proposed SolutionIntroduce a configurable expired-link experience that detects when a campaign link has expired and presents users with a clear, user-friendly message instead of a generic error or failed landing page.Key FeaturesCustomizable expired-link messaging Clear explanation that the communication link has expired Option to redirect users to: The latest version of the communication A help/support resource Admin-configurable expiration messaging and destination URLs Reporting on expired-link clicks to identify engagement after expirationBusiness ValueImproves employee experience and reduces confusion Decreases support tickets related to inaccessible communication links Preserves engagement with important communications after campaign expiration Provides administrators with greater flexibility and visibility into post-campaign activityUse Case An employee clicks a campaign link more than 14 days after receiving a communication. Instead of encountering a broken or inaccessible experience, they receive a friendly message explaining that the link has expired and are guided to the most current content or support resource.Priority Rationale Organizations using Employee Communications rely on campaign links to distribute important information. As adoption scales, a more graceful and intuitive expired-link experience becomes increasingly important to maintain trust, usability, and communication effectiveness.

    0
    Forum|Forum|1 month ago
    kyril.remillard
    kyril.remillardCommunity Manager

    Specialized Assistant: HRSD HR Business Partner Assistant2. On Roadmap

    On-demand talent insights for risks, performance, and succession gaps. Prepare for talent reviews with the same understanding as HRBPs. 

    0
    kyril.remillard
    Forum|Forum|1 month ago
    kyril.remillard
    kyril.remillardCommunity Manager

    Specialized Assistant: HRSD Manager Assistant2. On Roadmap

    Lead more and juggle tools & tasks less with help preparing for 1:1s, coaching for difficult moments, and better self-help for common questions.

    0
    kyril.remillard
    Forum|Forum|1 month ago
    9002467New Participant

    Add Copy Icon to Retain Formatting on Artey Answers1. New

    Description:Users have requested the ability to copy an Artey answer while retaining its original formatting, similar to the copy functionality available in other tools such as ChatGPT, Copilot, and GAILE.Requested Enhancement:Add a copy icon to each Artey answer that allows users to copy the response while preserving its formatting (e.g., line spacing, bullet points, paragraph breaks). The icon should function and appear similarly to the copy icons used in ChatGPT, Copilot, and GAILE — typically depicted as a paper icon with another paper behind it.Business Impact:This enhancement would make it significantly easier and faster for users to copy and paste Artey answers when sharing information with others requesting it, improving efficiency and ensuring the shared content remains clear and readable.Current Behavior:When a user copies an Artey answer, the formatting (such as line spacing) is stripped out, resulting in a less readable, unformatted block of text.Expected Behavior:When a user clicks the copy icon, the Artey answer should be copied to the clipboard with its original formatting intact, allowing it to be pasted elsewhere without loss of structure or readability.

    0
    Forum|Forum|1 month ago

    Roles & Permissions – Access Assignment Date for Governance1. New

    From a governance perspective, it would be valuable if the Roles & Permissions dashboard displayed when a role or permission was assigned to a user.Currently, administrators can see who has access, but there is no visibility into how long that access has been in place. Adding an Assigned Date column, along with filters (e.g., access older than 6 months or 1 year), would simplify periodic access reviews, access recertification, and compliance activities.This enhancement would strengthen governance by making it easier to identify, review, and validate long-standing user access.

    0
    Forum|Forum|1 month ago

    Bulk Role & Permission Management1. New

    Managing roles and permissions is currently a manual process, as administrators can only assign or remove access for one user at a time. This becomes time-consuming when onboarding large groups or updating access for multiple users.It would be valuable to add bulk role and permission management, allowing administrators to assign or remove roles for multiple users in a single action (for example, by multi-select or CSV upload).This enhancement would save time, reduce manual effort, improve the administrator experience, and make user access management much more efficient for enterprise customers.

    0
    Forum|Forum|1 month ago
    andrew.mairena
    andrew.mairenaCommunity Manager

    Table Visualization6. Delivered

    How are we improving the product?The Assistant presents eligible structured-data answers as an inline table instead of prose, making multi-row and multi-column results easier to scan, sort, verify, and reuse.View an example of Table VisualizationHow does it work?When a question returns consistent structured rows with at least two useful columns, the Assistant displays a short summary and a table preview of up to 15 rows. Users can sort by column, scroll across wide tables, see the total row count and snapshot time, and download the full dataset as a CSV.The table renders when the result is useful for scanning, comparing, sorting, verifying, or exporting. Single facts, explanations, one-column lists, chart-first results, sensitive data, and unclear permission cases remain in prose. If a table cannot render, the Assistant falls back to the standard prose response.Technical restrictionsAvailable on web.The in-chat table is a preview capped at 15 rows; the full result is available through CSV download.Data is a point-in-time snapshot rather than a live view.Results respect the user's existing permissions and only show records they can access.Fullscreen views, live refresh, saved or pinned tables, pagination, editing, custom charts, and cross-session table memory are not included in this release.

    2
    andrew.mairena
    Forum|Forum|1 month ago
    RyanPasca
    RyanPascaNew Participant

    Threshold of acceptability for enterprise search and knowledge articles1. New

    Goal: reduce frequency of bot responses that weakly match user intent. Reduce frequency of out-of-context bot responses.Product Idea: Would it be possible to add a feature allowing organizations using Moveworks to configure (perhaps within Moveworks Setup?) a threshold of acceptability for enterprise search?For example, a minimum matching score rating for knowledge matches to allow them to be surfaced. If there are no knowledge matches that meet the minimum matching score, then the bot would let the user know and offer to file a ticket or initiate live chat / agent handoff.I read about Moveworks Search “Ranking” at the link below, and understand Moveworks has specific ranking methodology to determine the priority order of which content to display.https://www.moveworks.com/us/en/resources/blog/enterprise-live-search-how-we-built-itHowever, this product idea addresses the scenario where Moveworks has nothing in its repository that meets the threshold and lets the user know, instead of citing a non-relevant or tangential topic. Instead, we would prefer the bot to reply with a statement along the lines of “I couldn't find a precise match for that. Would you like me to file a ticket for you?”We also envision this could workout when a plug-in triggers: It would be nice to have a threshold so that any enterprise search that comes up after a plug-in trigger, will have a very high likelihood of matching the plug-in content. So for example, when entering time, it would be best to only have articles that pertain to entering Time and not one for Expense (which it would most likely do in organizations where the two topics are so intertwined, and vocabulary across similar topic areas overlaps significantly.)I realize that if this feature existed, and an organization were to set the threshold too high, users could complain that the bot not knowing things. However if set too low, knowledge articles served would remain noisy, which can sometimes be the case currently.Here are a few Observations from Recent Chat Experience, testing interacting with the bot and asking it unique / obscure questions:The bot will occasionally ask the user to clarify if the question is unclear. It will say things like “It sounds like you may mean one of two things…”, without serving non-relevant articles. However, I did also find that the bot will tell the user when it cannot find a source that answers a highly-specific question, but it still will reply with links to articles that do not address the user’s direct intent. (happy to try to provide further examples if helpful)

    0
    RyanPasca
    Forum|Forum|1 month ago
    ramapr1New Participant

    Sensitive data Redaction and Data Masking for Moveworks Interaction data in Analytics1. New

    Moveworks Analytics currently shows user inputs and bot responses in plain text. While this level of visibility is extremely helpful for developers investigating unexpected bot behavior or addressing negative user feedback, exposing raw conversation text can create privacy and compliance concerns.Submitting this as a proposal to introduce native, configurable data redaction and masking capabilities within the Moveworks platform for raw interaction logs and analytics dashboards.Suggested capabilities would include:Built in regex based and AI driven entity detection to automatically identify and redact common sensitive information, such as salary details, performance ratings, and similar confidential data.The ability for tenant administrators to define custom regex patterns, keywords, or rules tailored to their organization’s specific privacy and compliance requirements.

    0
    Forum|Forum|1 month ago
    afleury
    afleuryInspiring

    Duplicate User Resolution & Account Prioritisation1. New

    Idea:Moveworks can already identify duplicate users, but there is currently no simple way for admins to resolve or prioritise which account should be treated as the authoritative record.ProblemMany organisations have multiple user records with the same email due to contractors, rehires, identity migrations, or HR system design. When duplicates exist, user attributes such as location, cost centre, manager, or department can be sourced from the wrong profile. Administrators must manually investigate and clean data in source systems.Suggested Enhancement Add a Duplicate User Resolution feature that allows admins to:Select the preferred record when duplicates are detected. Configure prioritisation rules (e.g. Team Member > Contractor > Short Term). Set source-of-truth precedence for user attributes. View and remediate duplicate users from a single admin interface.BenefitsReduces manual administration. Improves user identity matching accuracy. Prevents missing or incorrect profile attributes. Helps customers with complex identity environments without requiring perfect source-system data hygiene.I can provide a ServiceNow support case if you want to look into this further. DM me.

    0
    afleury
    Forum|Forum|1 month ago
    afleury
    afleuryInspiring

    Generative AI Search built into Moveworks Community portal.1. New

    Idea: Add a Generative AI Search capability into the Moveworks Community to assist customers and Moveworks team with quickly discovering information.Think of it like having a Perplexity or Google search built into the Community search page :) Benefits:AI-Powered Summaries: Generative AI can create concise summaries of search results, helping users quickly grasp the main points without having to read through multiple sources, Enhanced Search Experience: These summaries often include bullet points, images, videos, and citations, making the information more accessible and engaging.  Contextual Understanding: The AI adapts to user behaviour and preferences, offering personalized recommendations and insights. Interactive Features: Users can interact with the summaries, such as clicking on highlighted sections to get more detailed information or continuing the conversation with the AI for further clarification.

    1
    afleury
    Forum|Forum|1 month ago
    9002467New Participant

    Moveworks Displays "Reopen Issue" Option for RITMs That Cannot Be Reopened1. New

    Description:Artey currently presents colleagues with an option to reopen a previously submitted ServiceNow Requested Item (RITM) during conversational interactions. However, the underlying integration does not support reopening requested items, resulting in a poor user experience where users are offered an action that ultimately cannot be completed. As a result, colleagues may attempt to reopen requests through Artey only to encounter an error or unsuccessful outcome, creating confusion and reducing confidence in the assistant. Requested Enhancement:Update the Moveworks ServiceNow request management experience to validate whether a request type supports reopening before presenting the option to the user. If reopening is not supported for a given record type (such as RITMs), Moveworks should:Suppress the "Reopen Issue" action entirely for Requested Items, or Display a clear message indicating that reopening is not supported and provide alternative guidance, such as submitting a new request or contacting the appropriate support team.Business Impact:Eliminates misleading action prompts within Artey. Reduces colleague confusion and failed interactions. Improves trust in the assistant by only presenting supported actions. Decreases unnecessary support inquiries related to request reopening failures.Current Behavior:Artey offers users the ability to reopen a requested item (RITM), even though the action is not supported by the underlying process. Expected Behavior:Artey should only present a "Reopen Issue" option when the associated record type and workflow support reopening. Unsupported request types should not display the option. Acceptance Criteria:Moveworks validates reopen capabilities before displaying the action to users. RITMs that cannot be reopened do not display a "Reopen Request" option. Users receive clear guidance when reopening is unavailable. No failed reopen attempts occur for unsupported request types due to a presented Moveworks action.

    0
    Forum|Forum|1 month ago
    afleury
    afleuryInspiring

    Auto-map input arguments from HTTP Actions into Compound Actions and Conversation Processes1. New

    OverviewIt would be helpful if Agent Studio could automatically import or sync input arguments from an HTTP Action into the related Compound Action and Conversation Process.Today, inputs defined in an HTTP Action often need to be manually recreated or mapped again in the Compound Action, and then mapped again in the Conversation Process. While manageable for smaller actions, this becomes increasingly time-consuming and error-prone as actions grow in complexity.ExampleA ServiceNow Change Request action might require fields such as:short_description description start_date end_date risk_impact_analysisThese inputs are already defined within the HTTP Action, yet they must still be manually carried through multiple layers before the action can be used conversationally.This results in the same schema effectively being maintained three times: HTTP Action↓Compound Action↓Conversation ProcessSuggested ImprovementIntroduce an option such as:Import input arguments from HTTP Action Auto-map inputs Sync action schemaWhen enabled, Agent Studio would automatically propagate input definitions through the action chain while preserving:Field names Data types Descriptions Required/optional settings Default values Validation rulesBuilders could still override mappings manually if needed.BenefitsReduce repetitive configurationBuilders should not need to recreate the same inputs multiple times across different layers of the platform.Reduce mapping errorsThe more times a field is manually mapped, the greater the chance of:Missing fields Incorrect parameter mappings Out-of-sync schemas Placeholder values being accidentally passed throughFaster development and testingLess time spent maintaining mappings means more time spent:Building business logic Refining user experiences Testing new ideas Delivering value to end usersEasier maintenanceWhen an HTTP Action schema changes, updates could automatically flow through the action chain instead of requiring manual updates in multiple places.Why This MattersThis may be partially addressed by future capabilities such as Tool Architect, but there is still significant manual configuration required today when building actions.The biggest impact is not the time spent clicking through mapping screens. It's the interruption to the development flow.When experimenting with ideas, repeatedly recreating or remapping inputs across HTTP Actions, Compound Actions and Conversation Processes creates friction and slows iteration.For builders who enjoy exploring new use cases, prototyping solutions, or developing outside normal work hours, this repetitive setup work often becomes the limiting factor. Time that could be spent improving the experience, testing new patterns, or creating innovative solutions is instead spent maintaining mappings.Reducing this overhead would make Agent Studio more enjoyable to build in, encourage experimentation, and allow builders to focus on solving business problems rather than managing plumbing.Guiding PrincipleMap once, consume everywhere.Define an input once and have it available throughout the action chain, rather than maintaining the same schema across multiple layers.

    0
    afleury
    Forum|Forum|1 month ago
    ramapr1New Participant

    Ability to Customize User Consent Messaging for HTTP Connector Authentication4. Future Consideration

    When a user attempts to access a plugin connected to a user-consent based authentication connector for the first time, the Moveworks bot currently displays a default system generated message prompting the user to authenticate. However, this message does not clearly instruct users on the action they need to take to proceed.For many non-tech users, the prompt can be ambiguous and they may not realize that they must click the authorization button and complete the authentication process. This can lead to confusion, failed plugin usage, and additional support requests.Submitting this idea request to propose allowing customers (developers) to customize the authentication prompt message shown by the Moveworks bot during user consent flows. Providing the ability to modify or override the default system message would allow orgs to add clearer, more user friendly instructions tailored to their users.For example, the customized message would look like:Please click the button below and complete the authentication process to allow the Moveworks bot to securely retrieve information you requested.Allowing such customization would improve user experience.

    6
    Kevin Mok
    Forum|Forum|1 month ago
    vinitbKnown Participant

    Simplify User Consent Authentication Flow1. New

    SummaryUsers are failing to complete the connector authentication flow because the current consent message is unclear and the button is easy to miss without a call-to-action .ProblemWhen a connector requires user consent, Moveworks displays a message that leads with what it can't do (e.g., "I can't do XYZ..."). User feedback shows that most people stop reading at that point and never see the button prompt — causing them to abandon the flow entirely.Two specific issues:Message framing — Opening with a negative statement causes users to disengage before reaching the action they need to take. Button label lacks a call to action — The button is labeled with the connector name only (e.g., "SYSTEM"), which doesn't signal to the user that they need to click it.Current Experience We also attempted a workaround by renaming the connector to "Connect With SYSTEM" to make the button more descriptive. However, this causes Moveworks to use the same name in the preceding sentence, resulting in grammatically incorrect messaging: "Connect with SYSTEM isn't connected." Attempted Workaround  Requested SolutionsOption 1 — Simplified Consent Message (Preferred)Replace the current message with a clear, action-oriented prompt: Please grant access to [Connector Name] by clicking the button below.[BUTTON] This approach is direct, positive in framing, and immediately tells the user what to do. Option 2 — Independent Control Over Button Label and Message TextAllow admins to configure the button label and the accompanying message text independently, so the button can have a meaningful call to action (e.g., "Grant Access") without affecting the connector name displayed in other parts of the message. ImpactThis change would directly reduce authentication drop-off. It improves the experience for all users who interact with connectors requiring consent.

    2
    DIANA.TWC
    Forum|Forum|1 month ago
    RanjiniNew Participant

    Title: Routing multiple HTTP error status codes without deep try_catch nesting1. New

     Hi everyone,This is a continuation of my previous post: Extracting dynamic JSON error messages from 4xx/5xx responses in a try_catch block.Because the JSON payload is dropped when an HTTP action hits a 4xx or 5xx status code, we are discussing a workaround with our API team: having them provide highly specific, unique HTTP status codes for every single type of business error (e.g., 422 = “Error Message 1”, 423 = “Error Message 2”, 424 = “Error Message 3”). This would theoretically allow us to hardcode specific, static fallback messages for each error scenario.The Challenge:Agent Studio only allows one catch block per try. If the API returns 10 different status codes and we want to show 10 different static messages, we can't simply use a switch expression inside a single catch block because the HTTP status code of the failed action isn't exposed as a variable in the Data Bank.Because of this, we are forced to write deeply nested try_catch blocks using the on_status_code filter to route each specific error. If we have 10 different error codes, this results in massive, hard-to-maintain YAML nesting.My Question:Is there a cleaner design pattern or workaround to route multiple status codes to different static messages without this deep nesting? How are others handling granular, status-code-based error routing in Compound Actions?

    1
    Kevin Mok
    Forum|Forum|1 month ago
    christine.turgeonKnown Participant

    Persistent Smart Link in Employee comms1. New

    Links in employee comms currently expire after 14 days. For people going away on vacation and interacting with a comm upon their return, causes complaints!!!!

    0
    Forum|Forum|1 month 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