Skip to main content

Get Started

The roadmap, product ideas, and product plans are subject to change without notice. This roadmap plan is the current plan for new capabilities in the company’s product lines. However, 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

    986 Ideas

    M
    marissa.lacombeParticipating Frequently

    Update reasoner with date-awareness for content relevancy1. New

    Problem StatementAt CVS Health, conflicting information across multiple sources is a recurring challenge. Often, newer content exists alongside outdated versions on older sites, leading to confusion and incorrect answers. Current reasoning systems do not adequately account for content freshness, as published dates are not factored into relevancy scoring.Proposed SolutionIntroduce a product upgrade that integrates date-awareness into content relevancy algorithms. This enhancement would allow the system to prioritize and rank information based on temporal attributes, ensuring that the most current and authoritative content surfaces first.Key FeaturesMulti-Date Consideration: Incorporate created, updated, and published date (or a weighted combination) into relevancy scoring. Dynamic Ranking: Adjust search and reasoning outputs to favor the most recent and accurate content. Configurable Rules: Enable administrators to define how date attributes influence ranking (e.g., prioritize updated date over published date). Conflict Resolution: Automatically flag and deprioritize outdated or superseded content to reduce misinformation.

    0
    M
    Forum|Forum|2 months ago
    M
    max.matuzovNew Participant

    Not to respont to "Am I manager?" type of queries with wrong information, when that info is not available1. New

    Current Issue: Senior Leader with direct reports asks MW bot a question about his/her level using a query like “Am I manager”. MW bot responds with “No, you’re not” while in reality that person is of course a manager.  Expected behavior” Since bot doesn't know level of that person,  as user’s role details are not mapped  -bot should respond with “I don’t have that information”.It is ultimately a bad user experience when bot serves incorrect information. Support says this current behavior is expected as bot not having  manager information assumes that user is not a manager.

    0
    M
    Forum|Forum|2 months ago
    E
    emkellyParticipating Frequently

    Alerting For Employee Comms Campaign Failures1. New

    It would be great to have more alerting connected to campaign failures or successes. Either in-bot or an email notification that a campaign has been completed would allow important stakeholders who are connected to a campaign but not actively checking the employee comms module to ensure that their campaign has been delivered. This idea arose because we had a scheduled campaign failure and I did not realize the message hadn’t been delivered, until hours later.

    0
    E
    Forum|Forum|2 months ago
    A
    Ajay ChikaneNew Participant

    Simplify Access Configuration for Employee Communication Feature in Moveworks1. New

    Currently, even when a user has admin access in My Moveworks, they are unable to send Employee Communications without completing additional configuration steps.To send employee communications, users must manually configure the following: Navigate to Moveworks Setup → Notification Setup → Additional Controls Enable permissions for the Employee Communication feature This process adds unnecessary complexity for admins who already have access to both environments.We request an enhancement to automatically enable Employee Communication permissions for users with the Employee Communications (E-Comms) role, eliminating the need for additional manual configuration.Expected:  Users with the Employee Communications (E-Comms) role can send communications without additional setup. The system automatically grants necessary permissions under “Notification Setup → Additional Controls.”

    0
    A
    Forum|Forum|2 months ago
    J
    João Durand

    Triage Improvement1. New

    Hi Community,At our company, we were planning to use triage - however, the model’s precision hasn’t been ideal, partly due to data quality issues.We’ve been exploring ServiceNow Predictive Intelligence to retrieve the top 10 results using either classification or similarity models on our incident data.Our proposed improvement is to introduce an LLM (Large Language Model) to refine the prediction. The idea is for the LLM to evaluate the top 10 results from the ML mode - along with the description of each categor -  to determine the most accurate classification.We believe this could significantly increase the precision of both classification and similarity models, and in some cases, even replace the need for manual agent routing.Assuming triage currently uses OpenAI embeddings for indexing, implementation would be straightforward: Continue indexing all existing incident data, category descriptions, and service information. Use a RAG  approach to retrieve the top 10 results based on the user query. Have the LLM select the best match. Alternatively, using the classification model, we could: Retrieve the top 10 classification results based on the user query. Let the LLM determine the final category. Apply a confidence threshold (e.g., 70%). If the model’s precision is 60%, only high-confidence results go to the LLM, since the correct category is usually within the top few predictions. If results fall below the threshold, the ticket could be routed to an agent for review.The same logic applies when using similarity model - retrieve the most similar incidents, then have the LLM choose the best one.Additionally, since most of our agents follow knowledge articles linked to categories, we could extend this approach: Retrieve the top 5 relevant knowledge articles based on user issue. Have the LLM analyze them and select the one with the best category match. This could effectively automate L1 routing. Just some thoughts I’m planning to implement 🙂It might be worth considering this approach in genera - especially when ML alone isn’t sufficient due to data quality limitations. 

    0
    J
    Forum|Forum|2 months ago
    J
    JBouleyBBC25New Participant

    End User Conversations Transcripts For Closed Tickets in ITSM1. New

    Hello,In our ITSM our bot will receive instructions or utterances to close a ticket. As an agent we do not see the conversation leading to this decision, only the end result of our bot closing the ticket with a message stating “User Name said: Ok to close the ticket”. This could also be determined by utterances spoken and we’d like those interactions with our bot sent as a transcript to the ticket. This information can let our agents know if a ticket was closed due to lack of knowledge, our bot’s ability or even frustrations with the interactions. This will allow us to bring better resolutions to our users for future interactions.

    0
    J
    Forum|Forum|2 months ago
    M
    mthameParticipating Frequently

    Enable Live Agent handoff to other systems while keeping interaction within Teams/Slack1. New

    Today we have agent live chat interaction in SNOW. We have a new MSP that wants to have live chat handled in Ring Central (they use InContact). The issue is the it would be via URL that would redirect the end user to a different web portal. This is a poor user experience. It would be great if MW had a way to interact with other live chat instances but keep the chat in the bot via Teams/Slack.

    1
    bethany.vanderheiden
    Forum|Forum|2 months ago
    M
    MauricioParticipating Frequently

    Side Bar Panel Color Customization for Web AI Assistant1. New

    Allow admins to customize the side bar background color for AI Assistant on the Web.    Allow admins to replace Moveworks logo with Company logo on top left side bar panel  

    1
    M
    Forum|Forum|2 months ago
    J
    jeremy.spearsNew Participant

    Dark Mode for AI Assistant on Web1. New

    Allow users to toggle Dark Mode on and off.

    1
    M
    Forum|Forum|2 months ago
    C
    colin.schmalleNew Participant

    Attachment field types for ingested forms for Jira1. New

    Attachment field types are unsupported for ingested forms for Jira. It would be great to have attachments be an option for field types as we have users submit screenshots and PDFs of various types when creating tickets. 

    0
    C
    Forum|Forum|2 months ago
    R
    ryanKnown Participant

    Route Creator Studio API Calls through Moveworks Agent4. Future Consideration

    Follow up to this post: Route Creator Studio Connector through Moveworks Agent | Community The Moveworks Agent allows for integration of Moveworks platform into On-Prem systems.We have a Moveworks Agent installed to be able to pull data from our on-prem Confluence for knowledge ingestion; however, the same Moveworks Agent cannot be used in Creator Studio in order to query our on-prem Jira instance. Similar to how ServiceNow allows API calls to be routed through the MID Server, Creator Studio should allow API calls to be routed through a Moveworks Agent, if one is installed.

    3
    R
    Forum|Forum|2 months ago
    P
    pavithra.babu

    Ability to Start Live Agent Chat from Ticket Notifications1. New

     Without the ability to have the button to start a live agent chat from ticket notifications, the user needs to explicitly ask to start the live agent chat which treats it as a disconnected interaction.

    1
    M
    Forum|Forum|2 months ago
    M
    MikeINew Participant

    Include option to remove "thinking" process4. Future Consideration

    The visual created by the “thinking” process occurring and then being replaced by the answer/response can be jarring or distracting. I’d like to have the option to chose a single line of text such as “Working on your request. You’ll see your response here soon...” or simply responding with an emoji to show that the bot has your request. 

    3
    DIANA.TWC
    Forum|Forum|2 months ago
    Y
    YMRNew Participant

    EXI: Use Work Notes and Resolutions to identify1. New

    Users are notorious for providing less-than-ideal descriptions of their Help Desk issues. It would be ideal for EXI to also leverage work and resolution notes (not just ticket description) when identifying ticket trends. (Similar to how Knowledge Studio leverages that data to write/suggest knowledge articles). Thanks!

    0
    Y
    Forum|Forum|2 months ago
    C
    Christopher RNew Participant

    Message buttons - ask the bot a question1. New

    Hi,For comms messages sent using the bot, would it be possible to add a new button type?Our idea is to have a button that users can press to ask a pre-populated question. When the user clicks this button, a message will be sent to the bot as though the user typed it. The bot will then respond.The idea behind this came from our new-starter comms. When a new starter joins, we send them a bespoke message using the bot. To encourage engagement, we had the idea of including a few pre-populated questions in this message, that the new starter could select. This would start a conversation without the user having to type anything in.Thanks

    0
    C
    Forum|Forum|2 months ago
    J
    jeremy.spearsNew Participant

    Conversation History Retention1. New

    To better support our Client’s audit requirements, I am looking for the ability to remove the chat history from the interface (Slack, Teams, Web) after certain duration for a targeted group.  Example: our frontline users would only see their interactions within the bot from the last 24 hours.  We would still want all the conversation data available in Analytics.

    0
    J
    Forum|Forum|2 months ago
    afleury
    afleuryInspiring

    Native ServiceNow Form Support in Moveworks Web AI Assistant1. New

    Vision:Enable full native rendering and interaction with ServiceNow forms—including Client Scripts, UI Policies, Catalog Client Scripts, and UI Actions—directly within the Moveworks Web AI Assistant. This would allow users to complete forms without leaving the assistant, creating a seamless self-service experience.Why Now?With ServiceNow acquiring Moveworks, there's a unique opportunity to align platform capabilities. Moveworks may now have the technical control to support JavaScript execution safely within its Web AI Assistant, and ServiceNow can provide the necessary form logic and rendering components.💼 Business Value PropositionFrictionless User Experience: Users can complete complex forms directly in the Web AI Assistant, reducing drop-off and confusion. Increased Adoption: More users will engage with self-service workflows when forms are accessible and functional. Platform Synergy: Leverages the shared ownership between ServiceNow and Moveworks to deliver deeper, native integration. Reduced Support Load: Fewer tickets and manual interventions as users resolve issues independently via intelligent forms.

    0
    afleury
    Forum|Forum|2 months ago
    mitchell.wood
    mitchell.woodNew Participant

    Data Ingestion raw logs1. New

    The new data ingestion status page is fantastic. To diagnose potential issues, could there be a way to download the raw log data for diagnosis? If we get this info, it may assist with diagnosing if the issue is on the customer side or Moveworks side. If we can see it is with the customer side, would could go out, correct those issues and then see if the next ingestion run takes that corrected document. For example, if a PDF does not get ingested, raw logs might point out that an unsupported font was found, or that the document only contained embedded pictures instead of text so it was ignored.  With the logs we could better adapt any issues to the ingestion for the bot I have attached a screenshot of where I could envision the download button per ingestion run would go to really narrow down where potential issues may occur  

    0
    mitchell.wood
    Forum|Forum|2 months ago
    M
    marissa.lacombeParticipating Frequently

    Ability for the copilot to reply with explicit answers without also doing a knowledge search1. New

    CVS Health has a need to our assistant to reply with explicit answers that we define rather than doing or including a knowledge search in its response.  This feature was previously available with paths but with the new agent studio and agentic paths, a knowledge search is also being conducted. This is impactful as there are some situations where we find very outdated knowledge. The team needs time to clean it up and as a stop gap we need to publish the correct answer. Since Moveworks doesn’t take publish date into consideration, old outdated content is still sometimes used.  In summary, we need a simple, scalable way to provide scripted answers to colleagues without leveraging the copilot knowledge search feature. 

    0
    M
    Forum|Forum|3 months ago
    nicole.hulst
    nicole.hulstKnown Participant

    End User Notification controls in Copilot4. Future Consideration

    I saw in the Copilot feature overview that the unsubscribe etc are no longer possible in Copilot. For us this is a really important feature as it helps retain the users that have a lot of tickets open because they act as kind of a superuser for other people and open tickets for them. They get overwhelmed with notifications and like to mute some of them but would without that feature mute the bot entirely. Which would lower our active users significantly.Please bring that useful feature back, I don’t understand why it was not considered. 

    12
    N
    Forum|Forum|3 months ago
    D
    DanSpenglerNew Participant

    Manager-facing messages in software provisioning4. Future Consideration

    An information field in the software provisioning configuration page, most likely following the Additional Questions section, that allows us to provide request-specific context for the request to an approving manager who may not be very familiar with the software. This would be information the approver needs to know when determining whether the request should be approved or denied.  This information might include licensing/subscription costs, the purpose of the app, whether the request involves access to sensitive information, etc.Currently there’s only a field to prompt the requester for answers.  Some of this information can be shoe-horned into those question fields, but that provides a poor user experience.  The end user should not see these messages.If the provisioning strategy is role-based, there should be a separate such field for each configured role.

    3
    S
    Forum|Forum|3 months ago
    2613196
    2613196

    Friendly Naming and Notes Support in Moveworks Studio4. Future Consideration

     To improve clarity and maintainability of complex workflows in Moveworks Studio, I’d like to request the ability to assign friendly names and contextual notes to various elements such as actions, activities, and scripts—especially within compound actions and the visual editor. This enhancement would significantly improve collaboration, debugging, and onboarding for new team members.Key aspects of the request:Allow users to assign custom, human-readable names to: Actions Activities Scripts Compound actions (especially in Moveworks Studio) etc Enable inline notes or annotations that: Appear as comments in code view Display as visual notes or tooltips in the visual editor Ensure that switching between code and visual modes preserves these friendly names and notes Optional: Provide a toggle or UI element to show/hide notes for a cleaner workspaceThis feature would enhance usability and make complex workflows more intuitive and maintainable.Example of a layout. 

    2
    kyril.remillard
    Forum|Forum|3 months ago
    2613196
    2613196

    Conflict Engine for Managing Plugin Overlap in NLP Systems5. Not Enough Info to Make Decision

    Overview:In systems that utilize multiple plugins to fulfill user requests—especially when those plugins serve related but distinct purposes—it can be difficult for the NLP engine to automatically determine which plugin is most appropriate. This often results in multiple plugins being triggered simultaneously, leading to redundant or confusing outputs.To address this, I propose the implementation of a Conflict Engine: a configurable component that detects potential plugin conflicts and prompts the user to select the most relevant plugin for their intent.Key Features: Conflict Detection Logic The Conflict Engine would activate only when multiple plugins that are eligible to respond to a request, but their purposes are distinct enough to warrant user input. For example, one plugin may retrieve live event data while another provides historical comparisons from SQL. User Prompting Mechanism When a conflict is detected, and the offending plugin’s are enabled as part of a Conflict Engine the system would present a prompt listing the relevant plugins along with short, curated descriptions. The user can then select the plugin that best matches their intent. Custom Plugin Descriptions Descriptions shown in the prompt would be defined within the Conflict Engine settings, rather than pulled from the plugin metadata. This ensures clarity and avoids NLP-specific helper text that may confuse end users. Selective Plugin Participation Developers can opt a plugins int the Conflict Engine via a checkbox and select a configured Conflict Engine from a dropdown setting. This ensures that only relevant plugins are considered during conflict resolution and avoids interference with plugins that serve as dependencies or support functions. Considerations:The Conflict Engine should not interfere with plugin chaining or dependency resolution. It should only activate when multiple plugins could independently fulfill a user’s request. Plugin grouping and tagging could further enhance the system’s ability to detect and resolve conflicts. A fallback mechanism such as a timeout should activate in case the user does not respond to the prompt (e.g., default to non Conflict Engine behavior). Conflict Engines could be created/Managed under Data Type, or similar.Benefits:Improves user experience by reducing ambiguity and redundant outputs. Enhances system transparency and user control. Provides a scalable solution for managing plugin complexity as systems grow.

    1
    Ajay Merchia
    Forum|Forum|3 months ago
    DIANA.TWC
    DIANA.TWCInspiring

    Bring back ‘buttons’ for Agent Studio4. Future Consideration

    Can we have interactive buttons available again for Agent Studio?Previously, this feature was only supported in Classic Studio, which is being phased out soon. We’ve been developing several use cases that rely on active user input, and the lack of buttons is creating friction in the experience.More teams are requesting approval workflows through our chatbot. While the interactive button options can be done natively with ServiceNow, it won’t be possible for other API-based use cases, which could make the experience inconsistent and confusing for end users.Additionally, many of the plugins showcased in the AI Agent Marketplace display buttons as part of their interface. Does this indicate there’s already a roadmap for bringing this functionality back to Agent Studio? 

    1
    Ajay Merchia
    Forum|Forum|3 months ago
    S
    sdzwonkowskiNew Participant

    Feature Request: @ the bot in conversations1. New

    It would be beneficial to have the ability to @ our bot in conversations.  For example I am conversing with a co-worker and they ask a question.  I could @moveworks (insert bot name) to provide the answer in our conversation.  Similar to what Grok does on X.

    0
    S
    Forum|Forum|3 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
    Terms & ConditionsCookie settingsAccessibility statement