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

    1123 Ideas

    Ajay Merchia
    Ajay MerchiaCommunity Manager

    Plugin reporting6. Delivered

    Key DatesTBDWhat is itAdd Creator Studio plugins to the Copilot insights dashboard. They already exist in some capacity, but we aim to evolve the way they are represented after our new Agentic Automation Engine is fully rolled out.FeaturesTBD

    3
    kyril.remillard
    Forum|Forum|4 months ago
    samujala
    samujalaEmployee

    Connector Consolidation6. Delivered

    Key DatesTBDWhat is it Use System Connectors inside of Creator Studio FeaturesTBD

    1
    kyril.remillard
    Forum|Forum|4 months ago
    Lucas Rollo
    Lucas RolloCommunity Manager

    Agentic Automation Engine 2.06. Delivered

    Key DatesLimited Preview: April 2025 Preview: Q3 2025What is itA collection of capabilities to build advanced AI agents with a full refresh to the four pillars of our Agentic Automation EngineFeaturesPlugin Decision Policy - Make deterministic decisions in your AI agent Slot Inference Policy - Control the slot extraction behavior of your AI agent Slot Validation Policy - Validate slot values before executing actions Custom Object Slot Resolvers - Convert any natural language to an API value by fetching & disambiguating Content Activities - Show KBs, Forms, & Text

    8
    kyril.remillard
    Forum|Forum|4 months ago
    Y
    YashvardhanNew Participant

    Allow Meta Tags/Fields in Service now Forms to be picked up by BOT1. New

    We would like the Moveworks Bot to be able to search service Now forms by the data inside the Service Now forms Meta Tags/Fileds.

    1
    J
    Forum|Forum|4 months ago
    Ajay Merchia
    Ajay MerchiaCommunity Manager

    Agent Studio6. Delivered

    Give every developer access to our AI Agent Marketplace installer, low-code Plugin Workspace, & second-generation Agentic Automation Engine.

    0
    Ajay Merchia
    Forum|Forum|4 months ago
    priya.kornalius
    priya.kornaliusKnown Participant

    Analytics + Raw Interactions -- . Gaps Identified in Ticket Interception Reporting Data1. New

    When I pull the ticket-interception report from the Analytics page, the data is incomplete. The report does not include the team or assignment group where the ticket was intercepted, nor does it show the KB IDs recommended by the bot, which we need for KB fine-tuning.Without this information, I’m unable to measure interception performance across assignment groups.I also checked the “Raw Interactions” table, but it does not provide filters for user email or interception-related attributes.As a result, we’re unable to present meaningful, team-level insights on the tickets intercepted by the bot, making it difficult to showcase success stories for each group.

    0
    priya.kornalius
    Forum|Forum|4 months ago
    R
    ramapr1New Participant

    Remove 700px minimum screen width restriction for Web Assistant1. New

    The Moveworks Web Assistant currently enforces a hard minimum screen width of 700px. The mobile device browser view narrower than this (most commonly iPhones in portrait, many Android phones), the Web Assistant refuses to render.Please remove the 700px minimum width restriction and make the Moveworks Web Assistant fully responsive across all screen sizes.

    0
    R
    Forum|Forum|4 months ago
    A
    Ajay ChikaneNew Participant

    Improve ADA Comment Notification Formatting in MS Teams4. Future Consideration

    When a user-facing comment is received via ADA's comment notification in MS Teams, the text is displayed in a single line regardless of its original formatting, such as line breaks and spaces. This makes it difficult for users to read and understand longer comments.Enhance the ADA comment notification to preserve the original formatting (line breaks and spaces) when displaying comments in MS Teams, ensuring better readability and user experience.  

    4
    kyril.remillard
    Forum|Forum|4 months ago
    W
    WPalmerNew Participant

    Employee Communications Segmentation1. New

    We have several departments that wish to also use MW Employee Comms.  However, there is no way to segment that and managing the long list of comms/surveys etc with no available filtering in the GUI has caused us to take pause on federating this module across various business units. Is there a plan to segment or provide filtering in the employee comms module?

    0
    W
    Forum|Forum|4 months ago
    G
    GmerNew Participant

    Add a trigger type for the backstop so that plugins can be run as a fallback option4. Future Consideration

    Looking for a solution to leverage an agent for a handoff. We would like to leverage an agent to gather data from a user’s experience if they hit the backstop and either offer open ended suggestions on next steps or alert teams that underlying data like KBs need to get updated or created.

    3
    Ajay Merchia
    Forum|Forum|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.

    1
    samujala
    Forum|Forum|4 months ago
    Simon Vassallo
    Simon Vassallo

    Password Expiry Notifications1. New

    Our password expiry notification start date is set to 14 days before the expiry date, providing a default notification cadence of 14, 7, 3, 1, and 0 days, as confirmed by the MW documentation and support team.For our specific needs, we would prefer to customise this cadence to 14, 7, and 1 days which is currently not possible.We look forward to a future release that will allow organisations the flexibility to tailor the notification cadence to their unique requirements. 

    0
    Simon Vassallo
    Forum|Forum|4 months ago
    C
    christine.turgeonKnown Participant

    Allow client to choose wether we want to remove or not the option for users to block the bot or not1. New

    We would like as client, to remove the possibility for our users to block the bot. We are sending important communications on outages or security updates, but they are not reaching everyone. It is for campaigns, but once we add approvals and other push notifications, for us it could apply to any plugin or functionality. 

    0
    C
    Forum|Forum|5 months ago
    T
    tedgrabinskiNew Participant

    CSAT Score and Feedback comments in Data_API1. New

    We used the Data_API to retrieve Moveworks data into our company Databricks environment.  We would like to retrieve the CSAT score information and the feedback/comment associated with the interaction.  We see that the data is not available in the Data_API.We would like to retrieve the CSAT information so that we can review scores and associated feedback to identify areas of improvement.  We would also like the raw details so that we can calculate CSAT scores based on organizations using our internal people and organization sources.   

    0
    T
    Forum|Forum|5 months ago
    J
    jaime.rennKnown Participant

    Brief Me Enhancements - stop bad file types/file sizes - give user feedback on bad uploads1. New

    We would like to request an enhancement in Teams ( and maybe AI Assistant on Web once Brief Me is enabled in gcch) - that it prompts users when they have uploaded a file type or size that Brief Me does not support.  Currently we have users very confused and getting frustrated when asking questions about documents they think they successfully uploaded and Iris is not responding to that data . Additionally - our company has thousands of documents that have embedded tables and images and i am getting feedback of users comparing search in pdf for a word to brief me and reporting that brief me is not reading the entire document.   As much as we try to tell users of the limitations - there are always some that don’t read the fine print and end up having a bad experience / attitude of the results.  If possible - enable Brief Me to alert users to the limitation on reading images or tables in the documents   OR ;)  make Brief Me able to read images and tables in the documents.

    2
    W
    Forum|Forum|5 months ago
    R
    raelee.busk

    Analytics Overview Confusion1. New

    Since switching to the new AI Assistant version of the bot, we’ve learned a lot about using and interpreting the analytics that come with it, and overall, the improvements over time have been great. That said, there are a few areas where enhancements could make a big difference in usability of the data without adding extra steps or the need to dig in to feel confident with the data.Some details, like formatting and consistency, are minor. The bigger challenge for us is the Overview page in AI Assistant Insights.For example, the report at the bottom of the page shows plugin calls categorized as unsuccessful, served, and used. While this is interesting, it’s hard to apply in a meaningful way. It often requires cross-referencing individual plugin insights pages to track activity and effectiveness, which adds complexity.It would be incredibly helpful to have options to filter this data, like viewing only served and/or used plugin calls and to click on categories to see relevant chat data directly. This would reduce the need to navigate to “View interactions” or dig through raw data with multiple filters just to understand interaction patterns.I’d love to hear how others might be using this data as it is right now, though. If anyone has suggestions, I’d be open to hearing them!

    0
    R
    Forum|Forum|5 months ago
    R
    raelee.busk

    Employee communications and the new Web Assistant1. New

    Only a handful of users at my company currently have access to the new Web Assistant, so most users still rely on the bot we built for Teams. We recently ran into an issue when we sent an employee communication to a group of users. During that time there was a brief outage between Moveworks and Teams, which caused the message to fail for all intended recipients.The confusing part came from the reporting. Even though none of the users received the message in Teams, the report still showed a 100% delivery rate because the Web Assistant was considered an available delivery path, even though none of these users actually use it.Bottom line, being able to specify the delivery channel would prevent this issue. If we can lock a message to Teams when that’s the intended channel, then the reporting can reflect the actual delivery outcome instead of defaulting to the Web Assistant and showing a false 100% success rate.

    0
    R
    Forum|Forum|5 months ago
    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|5 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|5 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|5 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|5 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|5 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|5 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|5 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|5 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
    Terms & ConditionsCookie settingsAccessibility statement