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

    1344 Ideas

    Back to top of the list
    jgilmourNew Participant

    Vetting (Content Curation) entire confluence spaces / google drives /etc4. Future Consideration

    Vetting sources is awesome and a great add to the platform. I would love to see the ability to be able to vet either:1. an entire confluence spacegoogle drive folder/shared drive an entire connectorWe have found that through revamping our content, there is a number of dedicated folders/spaces/etc that should be listed as authorative content. It would be great to just choose a space/folder/connector to make it vetted, rather than having to do individual knowledge pages one at a time. 

    2
    Penny Zhou
    4 months ago
    jgilmourNew Participant

    Vetted (Curated) Content - Community Voting4. Future Consideration

    It would be great to have our employee base have a way to submit what should be vetted vs not. Maybe this could be through an interaction with the AI Assistant where if relevant/accurate information is given back, it can be “voted” to be vetted, or a way for employees to easily state new articles/files/etc should be “vetted”. 

    2
    Penny Zhou
    4 months ago
    afleury
    afleuryInspiring

    Automated Testing Framework for Moveworks Creator Studio Use Cases4. Future Consideration

    Idea: Develop an automated testing framework for chatbots that periodically and automatically runs test cases to verify access, functionality, and performance. These tests should be executed by both admin and user roles and triggered following any Moveworks updates or changes.Key Features:Periodic and Automated Testing: Schedule tests to run at regular intervals and automatically after updates. Role-Based Execution: Ensure tests cover both admin and user roles to validate different access levels and functionalities. Comprehensive Coverage: Include tests for access, functionality, and performance to ensure all aspects of the platform are verified. Alert System: Implement an alert mechanism to notify the team immediately if any test case fails, ensuring quick response to potential issues. Custom Flow Validation: Ensure that all custom flows are tested to confirm they are not impacted by code changes.Benefits:Increased Confidence: Provide peace of mind that the platform is functioning correctly after updates. Early Issue Detection: Quickly identify and address issues before they impact users. Efficiency: Automate repetitive testing tasks, freeing up resources for other critical activities.Similar to Automated Test Framework - Now Platform - ServiceNow

    3
    afleury
    4 months ago
    afleury
    afleuryInspiring

    Model recommender, Prompt Optimizer, and Prompt benchmark for System Prompts4. Future Consideration

    I’ve tried the Agent Architect but didn’t have much luck with getting a good answer. My question related to what reasoning level and model I should use to process my payload to avoid deadline errors and it recommended GPT4o which had a harder time processing the information I was sending.On the prompt optimizer I was thinking of something similar to OpenAI’s prompt optimizer but trained for compatibility with your Agent Studio environment and documentation for System Prompts. It would also be useful to have a way to benchmark a prompt to quickly see the output without having to re-trigger another webhook payload. e.g. An option to replay a recent Webhook payload from recent logs.

    2
    afleury
    4 months ago
    BHernandezNew Participant

    Enhancement Request: Exclude Hidden Unily Content from Moveworks Ingestion1. New

    Please enhance the Unily connector so that content marked as Hidden in Unily is not ingested or used by Moveworks, even if it is published.Current BehaviorContent with isHidden: true is still ingested because the connector filters on isPublished and isTrashed, but does not currently account for the Hidden flag.Why This MattersWe use the Hidden status in Unily to:Temporarily disable content Prepare content for future release Quickly turn features/widgets on or offIngesting Hidden content causes unintended exposure of content that is intentionally suppressed.Expected BehaviorContent marked as Hidden in Unily should be excluded from Moveworks ingestion and usage.

    1
    rraj
    4 months ago
    Christopher RNew Participant

    Unily Connector - Don't Ingest Hidden Content1. New

    We’ve found that the bot returns all content from published Unily pages. This includes widgets that are hidden to those viewing the page, but available to those editing.Here are two examples of when this can be problematic:When a team is preparing sensitive content for an upcoming announcement, this should only be visible to page editors. Because of this issue, draft information is available to anyone with access to the bot, which is a compliance risk When a team hides a widget from display because it contains outdated information, this still serves in the bot which is problematic and reduces confidence in answers the bot givesWe’ve been informed that Unily has two APIs:The Content API which returns all content on a page (even content that is unpublished) The Search API which only returns published contentOur understanding is that Moveworks uses the Content API. Please could you fix this issue and ensure that only published Unily content is visible in the bot?

    2
    rraj
    4 months ago
    SudheerCommunity Manager

    Slack RTS Migration6. Delivered

    Faster, more scalable search in Slack, powered by Slack's real-time search (RTS) API — delivering improved Live Search results without changes to your existing Slack setup.

    0
    4 months ago
    Joel.MatiasKnown Participant

    Issues with Marketplace Installable Plugins2. On Roadmap

    Right now there is a bad user experience when installing plugins from the marketplace. When we install plugins that have actions/components that were already built from other templates it says to rename them because they need unique names. When we rename the component in the template it shows as if it’s accepted and allows to install the plugin but then it fails with the same error. The only workaround I found so far is to rename the component already installed, delete and reinstall the template. This is not a great experience because I then have to go back to the first plugin installed and update the components and delete the duplicate(renamed) one. It would be great if there was an option to note that it’s installed already so it doesn’t install it or some other version of that to avoid this.This recently happened with the Outlook Plugins I was installing and some of them have many pieces. 

    2
    Kevin Mok
    4 months ago
    Penny Zhou
    Penny ZhouCommunity Manager

    Multilingual Support UI Improvements2. On Roadmap

    In Assistant, we will display source citations in the original content language instead of automatically translating sources to your preferred language by default. Across both Assistant and Enterprise Search, we'll add an option to translate the displayed source into your configured messaging language. This keeps you connected to the original source context while making results more accessible in your preferred language.

    0
    Penny Zhou
    4 months ago
    willmurphyCommunity Manager

    GPT-5.2 Reasoning Engine (Basic)6. Delivered

    Updating Basic tier to GPT 5.2. Read more about the model upgrade program here.

    1
    4 months ago
    Jayanth MahalingamCommunity Manager

    Multimodal Support for Brief Me6. Delivered

    How are we improving the Assistant's behavior?We are improving the Assistant's "Brief Me" feature by adding multimodal support, which allows it to understand and answer questions about images—such as diagrams, screenshots, and charts—within uploaded PDF documents. This is achieved by converting images into text captions at upload time and indexing them alongside the document's text, making visual content searchable.Release date: September 18, 2026

    0
    4 months ago
    kyril.remillard
    kyril.remillardCommunity Manager

    Plugin Installation Merge Support6. Delivered

    When installing a new version of the same plugin, either from the marketplace or from a lower production environment, you can now selectively keep previously imported components – reducing duplication & simplifying updates.

    0
    kyril.remillard
    4 months ago
    Chaitanya GoliNew Participant

    Customizable Response for Sensitive Questions ( Toxicity functionality response)1. New

    Implement a feature that allows customization of the default response displayed when a sensitive question is detected. The current message—"I am sorry that I can't help you."—may not be sufficiently informative or helpful for users dealing with serious inquiries or issues.We recommend enabling the ability to replace this default message with a more meaningful, context-appropriate custom response that can better guide or support users.

    0
    4 months ago
    alexifrancoNew Participant

    Assignment Group Exclusion for Knowledge Studio Recommendations1. New

    Provide a configurable option in Knowledge Studio to exclude specific ServiceNow assignment groups from ticket ingestion and analysis used for knowledge recommendations.Certain assignment groups are managed by third-party vendors who maintain their own external knowledge bases. Ticket activity from these groups should not be treated as internal knowledge gaps.Knowledge Studio currently includes all ticket data, resulting in non-actionable and irrelevant recommendations from vendor-managed queues.Recommended solution: Enable assignment group–level filtering (denylist) to exclude selected groups from:Ticket ingestion Knowledge gap analysis Recommendation generation

    0
    4 months ago
    Chaitanya GoliNew Participant

    Sandbox Color Differentiation1. New

    Request to implement a different color theme for the sandbox environment to ensure clear visual distinction from the production environment and reduce risk of confusion.

    1
    4 months ago
    colemanCommunity Manager

    Employee Communications Refresh1. New

    When it comes to immediate impact from Moveworks bots, the Employee Communications feature is a clear front-runner. That said, when crafting campaigns, users are currently limited to basic emojis and the 5 basic design tools below.Additionally often chat messages won’t look exactly how you’ve drafted them in the editor. In Editor:Contains Line Breaks and Tab IndentsNo Line Breaks, No Tab IndentsThis request is to enhance this tool and add support for more rich text options across all supported chat surfaces. 

    0
    4 months ago
    StaizyNew Participant

    View Next/All Approval(s) button visible with no pending approvals4. Future Consideration

    In the Time Off Approvals connector, there are buttons to view next/all approvals even if there aren't any left in the queue. This causes confusion when there are no more approvals in the queue. We want to be able to hide the View next approval and View all approvals buttons if no more approvals are in the queue.There should be a config option or logic built into the connector to remove the button options if there are no longer any pending approvals in the queue. 

    5
    4 months ago
    andrew.mairena
    andrew.mairenaCommunity Manager

    Updated Reasoning Messages for Web only6. Delivered

    Making complex AI reasoning easier to digest and more transparent 

    0
    andrew.mairena
    4 months ago
    mfigueroacontreraNew Participant

    Unified Bot with Intelligent Mode Selection (Search vs AI Assistant)1. New

    InspirationApple Siri AI announcement (June 2026) introduces automatic mode detection for user queries. Simple searches default to Spotlight search results; complex requests route to LLM-powered explanations. This pattern creates a seamless unified experience without user friction or explicit mode selection.Problem StatementUsers interacting with Moveworks currently experience cognitive load when determining whether they need quick search results or deeper AI-assisted reasoning. This split mental model across different bot capabilities or interfaces reduces perceived simplicity and increases support friction for end-users.Proposed SolutionMoveworks implements a unified bot interface with intelligent query routing:Single entry point: Users always interact with one Moveworks bot.Automatic mode detection: The bot analyzes incoming queries and determines the optimal response pathway.Response modes:Enterprise Search mode (simple/direct queries): Returns curated knowledge base results, IT catalog items, HR policy documents, or employee directory records with minimal latency and maximum precision. AI Assistant mode (complex/nuanced queries): Leverages LLM reasoning for contextual analysis, multi-step guidance, or explanatory responses that benefit from natural language generation.No friction: Users do not select a mode or mode type. The bot makes this determination transparently.Business ValueUnified experience: Single bot builds user confidence and reduces learning curve across the organization. Reduced support load: Lightweight queries get fast answers without LLM overhead. Complex queries benefit from AI reasoning without forcing structured search workflows. Improved adoption: Employees default to the bot as a reliable all-in-one agent rather than navigating separate search tools or AI assistants. Operational efficiency: Query routing optimizes cost and latency by matching query complexity to appropriate infrastructure.Technical ConsiderationsClassification logic: Implement lightweight pre-processing to categorize queries (intent detection, keyword heuristics, query length, entity recognition). Avoid excessive latency overhead. Fallback behavior: Define graceful escalation if classification is ambiguous. Analytics: Track mode distribution, user satisfaction by mode, and accuracy of routing decisions to refine classification thresholds over time. Transparency (optional): Consider subtle UI affordance (e.g., "Search results" vs "AI insights" label) to help users understand why they received a particular response type without forcing explicit selection.Competitive PositioningApple Siri AI demonstrates this pattern as table stakes for modern AI assistants. Moveworks adopting this approach positions the platform as intuitive and frictionless, matching user expectations set by consumer AI products while maintaining enterprise-grade knowledge integration.

    0
    4 months ago
    deanatNew Participant

    In future roadmap: Can Moveworks Chatbot to be able to ingest read more complex tables, charts, and images like Copilot1. New

    Submitting this as we would like for the Moveworks conversational AI chatbot to be able to ingest complex tables, images, and charts (currently it looks like it can register simple html two-columned tables from our content) but would love for this to be on the roadmap (as currently other AI tools such as Copilot, Gemini, ChatGPT can intake such images and tables). Thank you,Deana

    1
    4 months ago
    afleury
    afleuryInspiring

    Adaptive Cards – Multi-line Textbox Usability (Web Assistant)1. New

    SummaryMulti-line textbox (Description field) in Web Assistant adaptive cards cannot be resized. Impacts usability vs expected behaviour in modern web forms. Problem StatementUsers cannot expand the Description field. Limits visibility of typed content. Creates friction when entering longer responses. Behaviour differs from other experiences (e.g. Teams variant handled separately but has the same issue). Current BehaviourFixed-size textbox in Web Assistant adaptive cards. No drag-to-resize or auto-expand capability. Expected BehaviourTextbox supports: Manual resize (drag handle) Auto-expand based on content length Scroll fallback only after max height reached ImpactReduced user experience in Moveworks portal flows. Slower form completion for Service Desk requests. Increased risk of truncated or poorly formatted input.Business ContextUsed in bot-fillable forms via Moveworks → ServiceNow integration. Affects high-volume request scenarios (e.g. Ad Hoc Request forms).Proposed SolutionEnhance adaptive card rendering in Web Assistant: Enable dynamic height for multi-line text inputs Add optional config flag for “resizable = true” Maintain parity with Teams or other supported channels where applicable Alternatives ConsideredNone viable currently (confirmed by Engineering as enhancement only). Success CriteriaUsers can comfortably enter long-form text without UI constraints. Improved completion speed and quality of inputs. Reduced agent follow-up due to incomplete descriptions.Current​​​​​​Future State - What it could look like 

    0
    afleury
    4 months ago
    Chaitanya GoliNew Participant

    Logging for Interactions Table Access in Analytics Module1. New

    Implement activity logging to capture and track user access to the Interactions table within the Analytics module. This enhancement would enable visibility into who viewed the data, when it was accessed, and potentially from where, supporting auditability, security monitoring, and compliance needs. The goal is to ensure that all access events are recorded and available for review, helping teams maintain transparency and control over sensitive interaction data usage.

    0
    4 months ago
    mmasiulisParticipating Frequently

    Add Approver Email Address to JSM Software Request Notes1. New

    Currently, when a software request is approved or rejected via the Moveworks AI assistant, an internal note is added to the Jira Service Management (JSM) ticket containing only the approver’s name.Due to JSM formatting limitations, we cannot reliably trigger automation rules using names alone. To resolve this, we would like to include the approver’s email address in that internal note. Access to the email address will allow us to parse the value and successfully build our required automation workflows.We receive a high volume of follow-up inquiries from users asking why their requests were rejected. Having the email address will allow us to build an automation rule that automatically tags the specific approver in the ticket and sends them a prompt to add their rejection reason, significantly reducing manual overhead for our agents.

    0
    4 months ago
    willmurphyCommunity Manager

    GPT 5.4 – Frontier Release6. Delivered

    Updating our Reasoning Engine to GPT 5.4.

    0
    4 months ago
    afleury
    afleuryInspiring

    Support Locale-Specific Date Formatting in In-Bot Fillable Forms1. New

    SummaryMoveworks in-bot fillable forms currently default to US date format (MM-DD-YYYY) and do not respect user or tenant locale settings such as en-AU (DD-MM-YYYY).ProblemDates appear in US format regardless of regional settings Creates ambiguity (e.g. 04/08/2026) for AU/NZ users Issue is consistent across MS Teams and Web AI Assistant ServiceNow correctly honours locale, highlighting inconsistencyExample below, date is in US format. Investigation OutcomeConfirmed by Moveworks Support and Engineering No configuration option to control date format Behaviour likely tied to rendering layer, not user settings No workaround available todayImpactConfusing user experience Risk of incorrect date submission Additional validation effort for Service Desk Reduced trust in bot-driven request accuracyRequestIntroduce support for locale-aware date formatting in in-bot forms, including:Automatic detection of user locale (preferred) Tenant-level locale override Optional field-level format control (DD-MM-YYYY, MM-DD-YYYY, etc.) Consistent behaviour across Teams, Web, and other platformsPriorityMedium–HighAdditional ContextThis is a basic expectation for global organisations. Lack of locale support is a gap for AU deployments and limits adoption of in-bot forms.Expected OutcomeDates displayed and submitted in Moveworks forms align with user regional settings, removing ambiguity and improving accuracy.

    0
    afleury
    4 months ago
    Show more activity

    Filter by product

    • All products
    • Analytics
    • AI Assistant
    • Tool 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
    • Channels
    • Assistant Platform
    Terms & ConditionsAccessibility statement