Product Forums

Managing all the connectors I have in Moveworks Setup is a lot and I want to be able to easily track when an API token is expiring for Moveworks in Atlassian for example to avoid degradation in our Moveworks Assistant due to expired credentials. How can I use Agent Studio to notify me 30, 15, 5, etc. days in advance before expiry? Is this possible?

Hello Moveworks Community! We are thrilled to announce a major expansion to the Moveworks Data API. Starting April week 1, 2026, we are evolving the API from a "user-engaged" model to a "system-wide" model by introducing visibility into System-Triggered Events.Currently, our Data API focuses on conversations where a user has actively participated. But we know that much of the magic of Moveworks happens proactivity—through notifications, ticket interceptions, and channel resolutions. This update brings that proactive power directly into your hands for deep analysis and reporting. What’s Changing?We are updating four core entities to include System-Triggered Events (Notifications, Channel/Ticket Interception reach-outs)Please note that these changes are ADDITIVE in nature and will not break any of your dashboards. However, to

We’re rolling out an upgrade to your Confluence integration to improve how content and permissions are handled.What’s changingWe are upgrading your existing Confluence connector to a newer version.As part of this process:A new Confluence connector has been created in your environment by Moveworks. This new connector runs in the background while your current integration continues to work as usual.What’s improvedSupport for attachments: Users will now be able to access Confluence files such as PDFs, Word documents, and presentations. Improved permissions handling: Access control will be more reliable and scalable, ensuring users only see content they have permission to access.What to expect during migrationThere is no downtime — your current confluence integration continues to work. You may notice a new Confluence connector in Setup. Thi

I want to automate adding/removing users in DL/Shared email box through Agent Studio. If the requestor is owner of the group then it is a straight-forward journey of adding/removing users in DL but if the requestor is not the owner then I am using “mw_generic_approval_request” in Compound Action to send the approval to the Owner of the DL. Is it possible to intercept the Approval/ Denial by the bot and then send a notification to the requestor that the Approval has been given and then proceed with adding the requested users to that respective DL.

Hi , I have a use case where I am using compound action to create buttons, i would like to give links to these button.orAre there any way to display the buttons with link using html tags. 

Hi everyone. I am here to learn how my ServiceNow Analyst role will evolve in this environment. 

Hi Team, While trying out the Beta Conversation API, I’m getting 404 API Not Found response. How can we resolve this or enable the beta Conversation API.

Hi,We have seen that late last year the Moveworks chatbot was not auto-scrolling to the beginning of the response in both the Moveworks web app, and the Embedded Assistant in ServiceNow. It seemed it was fixed briefly at the beginning of the year (end of Jan 2026 when MW branding changes were initially pushed), but now it seems like it is no doing the auto-scroll to the beginning of the response. Can we have this auto-scroll feature returned so that it works like it did at the beginning of the year in both the Moveworks Web App and in the ServiceNow Embedded Assistant?  Thank you,Deana

Hi Moveworks Community,I’m currently working on configuring Ivanti IT Knowledge articles ingestion within Moveworks via the following path:Moveworks Setup → Enterprise Search → Search → Configure Search → Classic Ingestion → Internal KnowledgeI wanted to understand how we can implement user-specific permissions or access control for knowledge articles ingested from Ivanti IT.Specifically: How can we ensure that only authorized users or user groups can access certain knowledge articles? Does Moveworks respect source-level permissions from Ivanti IT during ingestion, or do we need to configure access control separately within Moveworks? Are there recommended best practices for mapping user roles/groups between Ivanti and Moveworks to enforce these restrictions? Any guidance, documentation references, or examples would be really helpful. 

Previously I was able to open Analytics, click User Insights and then export a CSV list of all bot interactions. I could evaluate hundreds or thousands of interactions. This option is gone. Where did it go?Previously, I could go into Analytics, go to Plug-in Insights and scroll to Knowledge Gaps. This option is gone. Where did it go?It’s frustrating to not find critical information nor not be warned that these changes are coming. Even sorting community responses is exceptionally poor. Other data sources give you the option to sort by date. This a basic feature yet it is missing from the Moveworks Community. 

Hello Community!While Moveworks supports an Approvals skill out-of-the-box, I wanted to share a common architecture to create custom approvals via Agent Studio! Using Webhooks and Agent Studio, you can create a seamless, "in-channel" approval experience with full customizability that keeps workflows moving without forcing users to log into external portals.The Solution: Webhook-Driven ApprovalsBy leveraging Agent Studio Webhooks, you can process external events to provide users with real-time notifications and actionable buttons to approve or deny requests. Common workflows requiring approvals include:Software Access Requests Hardware Procurement Requests Travel & Expense

ProblemA common challenge in Agent Studio is how to serve grounded answers from public-facing documentation without building a full external ingestion pipeline.Teams often want the bot to answer questions using content that already lives on public websites, but they also want the experience to staygrounded in source material rather than general model knowledge transparent, with citations or traceability lightweight to implement and maintain targeted enough to return useful answers without introducing too much ambiguityThis becomes especially relevant when the source content is public documentation, such as help centers, product docs, compliance pages, or accessibility documentation.A good example is accessibility content. A user may ask about a specific capability such as Teams closed captioning, and the desired behavior is for the bot to answer from the correct Microsoft acc

Hello Community!We are excited to announce the upgrade from Triage 1.0 to 2.0! After the GA announcement of Triage 2.0 in Q4 2025, 40 customers have upgraded and have had incredible impact:Improved overall performance, a lift to Precision & Coverage, to route and categorize more tickets. Relaxed data requirements, allowing model training below 100 ticketsNow, we’re ready to bring the enhanced power of Triage 2.0 to all current Triage 1.0 customers!What does this mean for you?We already did the work to build the Triage 2.0 index in the background, without any disruption to your operations (

Good group this week. Ryan and I walked through the Golden Rule for compound actions, built a scheduled notifier from scratch with switch logic and for loops, and showed off the new Outlook calendar plugins that just dropped in Marketplace.What we covered:The Golden Rule — use compound actions instead of chaining actions to keep the reasoner's context clean Scheduled Plugins (Live Demo) — interval-based system triggers with switch statements and for-loop iteration Webhook Listeners — expose plugins as API endpoints for external systems, with HMAC, OAuth2, and JWT auth MCP Support (Roadmap) — coming Q2, import and customize tools from your MCP servers Outlook Calendar Plugins — 6 new Marketplace plugins for booking, canceling, and managing meetings Onboarding Use Cases — Marketplace Initiatives for mappi

Hi, Is there any consideration to reduce the delay on these data exports (this would to help with both testing result readout timeliness and post-go live results support to view employee feedback in real time instead of needing to wait a day or day+ considering UTC timing)? This would help a lot with quicker triage within our internal teams to improve the chatbot experience.

Announcement: Sunsetting Legacy Analytics SFTP Reports As part of our commitment to modernizing our data infrastructure and aligning with the Classic Bot deprecation, we are officially sunsetting legacy Analytics SFTP reports. These reports were designed to serve data exclusively for the Classic Bot experience. As we transition toward a more integrated AI Assistant environment, we are moving all reporting to our high-performance Data API and Product Dashboards.What is Changing?The following reports and their associated SFTP access will be deprecated: All Classic Bot usage and performance reports. daily_user_roster daily_triage_record

The Purple API Tool (https://docs.moveworks.com/agent-studio/quickstart-guide/purple-api-tool) has been broken since 3/17/2026. What's the timeline of this Purple API Tool being fixed?Now with the same session ID, webhook url and my API Key filled properly in all three fields, and webhook payload generated, when I clicked Trigger Webhook button, I kept getting "Error in API: An error occurred. You may be missing the API key in your input".

We are working on use case where we want the bot to respond to the users query of  filling the timesheet , the bot should respond with a table to fill the hours for the whole week , also a dropdown to select a date range like week or month , but as per my understanding the bot right now do not support the adaptive cards ? Am I right here ? Also I would like to know if anyone has built a similar kind of use case where bot prompts the end user with a table like structure to fill the data in and then we in the backend will be able to process it .  

Hello - has anybody tried displaying sorted results using Notify action within a for loop? We are invoking notify within a for loop and passing it an employee list that is sorted by the last name. However the results displayed are not ordered. It seems like notifications are sent at random. Kindly share any insights / solutions if you have encountered this.- for:      output_key: sent_notifications      each: employee      index: idx      in: data.merge_result.employees      steps:        - notify:            output_key: notification_result            recipient_id: meta_info.user.id            message:              RENDER():                args:                  full_name: employee.full_name                  country: employee.country                  total_pending: employee.total_pending                  preview_trainings: employee.preview_trainings                

Hi everyone,We're making the Enterprise Search section of Moveworks Setup clearer and easier to navigate. Starting April 6, 2026, you'll notice updated labels, a restructured navigation, and renamed connectors. These are display-only changes — no functionality, URLs, configurations, or APIs are affected.Why are we making this change?As we expand Enterprise Search and its configuration journey in Setup, the existing navigation labels had become confusing:"Enterprise Search" serves as both a product SKU name and a Moveworks Setup configuration page name, causing ambiguity on whether this page is linked to the SKU or not "Max Capacity" has already been coined in our new SKUs, and "Next Gen" connector labels were adding to the confusion on which connector to use where The new ingestion journey for Max Capacity connectors doesn't diffe

I have been working on setting up the connector for SharePoint/OneDrive Live Search for Enterprise search. I created the NG connector, and I was able to create the Enterprise search connector. I initially ran into an issue saving after validating the connector for the 2 Live Search options but I eventually got it saved. Now it shows in my list but as Not Enabled and it doesnt show in Enterprise search.Do I have to set up sharepoint ingestion or at least the ingestion settings as well for the connector to work? I only need the live search at the moment. 

I have a compound action:steps:  - for:      output_key: user_bookings      each: booking      in: data.list_of_user_bookings      index: user_index      steps:        - try_catch:            try:              steps:                - action:                    action_name: mw.get_user_by_email                    output_key: got_user                    input_args:                      user_email: booking.email                - switch:                    cases:                      - condition: data.lang == "es"                        steps:                          - notify:                              output_key: officespace_output1                              recipient_id: data.got_user.user.id                              resources:                                - name: instructions                                  dataty

I have a onboarding process that is initiated by a listener. The listener uses notify to contact the new hire’s manager. I need to collect information about what the new hire needs so notify has a button to start a conversational process. When this happens, the manager is asked for the information. However their response is initiating other plugins if there are some matching keywords. There will be some overlap here, so what are some suggestions from preventing the response from starting a new plugin?Note that this was working fine a month or so ago. Since then many new plugins were made which might be conflicting with this. I am leveraging many applicable positive and negative prompts in these new plugins.

Lighter session this week, but we still covered ground. Ryan and I walked through the new image delivery feature in Notify, unpacked when to reach for Python scripts over DSL, and ran through a chunk of the Agent Studio roadmap — Agent Architect V2 and MCP support included.What we covered:Media Delivery (Image URLs) — send images to users via Notify's new image_urls field Python Scripts vs DSL — when to pick Python over mappers for string building, nested data, and math Plugin Export & Dev-to-Prod — export flow walkthrough plus versioning on the roadmap Verbatim Messages & Embedded Links — render templates with markdown formatting for inline links Agent Studio Roadmap — Agent Architect V2 vibe coding, one-click connectors, sharing & permissionsHere's the recording:

HI ,Any plans with an option to create the folders is Agent Studio platform so that we can manage our use cases in folder structure. Regards,Rajeev