Agent Studio

Hi All, How can I configure the “New Hire” functionality is employee comms.At the moment, our new users are being identified from ServiceNow user records, the condition will look like followingcreated : today user type is not functional OR externalRegards,Rajeev  

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?

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 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. 

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

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

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".

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                

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

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

 Hi , I am sending the teams nudge using moveworks send_message API, the nudge only works for 1 email id not for multiple. can someone please help here. following is the code for the reference.        var recipientEmail = event.parm1;// value being passed in event.parm1 is -> email1@example.com,email2@example.com        var summary = event.parm2;// nudge works with following hard coded values    //    emailRecipient = ["email1@example.com", "email2@example.com"];// following code is to get the list of string        var colSplit = recipientEmail.split(",");// logging result is [colSplit 1 -- object] gs.log("colSplit 1" + "--" + typeof colSplit); var arr = []; for (i = 0; i < colSplit.length; i++) { arr.push(colSplit[i]); }       try {

Hey Everyone,So I know when it comes to the AI Assistant, the graph.api access needs to be on the appliation level.That said, when it comes to agent studio can it work with graph.api access on the delegate level? We’re running into some issue with the access through our Global tenant and if we can use delegate access with Agent Studio that would open up a lot more doors for us faster.

I am using a listener to take in requestIds that start an automated process. When setting it up, there were some situations where the requestId was sent twice and I wanted to avoid the processing being called twice, so I added in Deduplication configuration in the listener. The request body being sent to Moveworks is always in this format:{“requestId” : “<id>”}Therefore for the deduplication, I added requestId as the Deduplication key (no spaces or quotes) with a 1 min window. However I am noticing that it is blocking requestIds that are not equal but are sent within the 1 minute timeframe. The difference between them in these cases is the last character in the requestId (ex ABC1234 vs ABC1235) In the logs, I am seeing one go through and “debounced_update” log entries for the other requestIds sent. I have no event filtering enabled for the 1 plugin that is associated to this listener. Please assist me in understanding the root issue and how to set this up correctl

Is it possible to display a QR code to a user via the bot? The agent architect makes it seem like there is but it’s suggestions do not work. If not, are there any roadmap items to include image displays via the bot?

In my application, all request bodies need to be form data with data as the key and the json body as the value. I am able to handle this in http actions with raw json body by having it be something like data={<insert body here>} and having the header of Content-Type=application/x-www-form-urlencodedI want to use the new data mapper functionality in http actions so it will handle escaping and such for me, however I cannot seem to find a way to get it to work with this setup. I have attempted numerous times with variations of data: <json to mapper syntax> , but the app always returns with a missing data element error. Is there any way to handle this currently?

Hey builders 👋I've been reviewing a lot of plugins lately, and the same slot mistakes keep showing up. They all pass in testing. They all break in production. So I wrote up the six patterns I see most often, with the bad config and the fix for each. 🚨 1. Using string for peopleThe #1 slot mistake I see. You're asking the engine to parse emails from free text.# Bad — forces the engine to parse structured data from free text- name: attendees description: "Comma-separated list of attendee emails like john@company.com, jane@company.com" data_type: stringUser says "invite John and the marketing team." Your string slot captures the literal string "John and the marketing team". The engine tries to parse that into emails. Fails. User tries "john@company.com, marketing-team@company.com". Engine parses it. But marketing-team is a distribution list, not a user.

This may not be related to Agent Studio specifically but it relates to a plugin I’m creating that prompts for user OAuth2.0 authorization so I thought I’d post here first.I'm looking for a way for users to be able to clear Moveworks authorization tokens after they've already made an authorization between their Moveworks account and some other application. For example, if a user has made an authorization between their Moveworks account and Jira, the user can remove their Moveworks connection in their Jira settings, but I don’t see a way for users to remove the Jira connection in Moveworks. With Moveworks still seeing the connection which is no longer valid, the plugin then returns authorization errors and doesn’t prompt for a new authorization to overwrite the existing authorization.I didn't find any documentation on this, and the instructions I'm given by Agent Architect do not work, for example asking the bot to manage connections or disconnect the application. Agent

I’ve built a plugin that sends notifications when Jira approvals are needed. The approvers of the Jira ticket receive the notification and have buttons to approve or deny the Jira ticket. In order to approve or deny, the user must first authenticate a Moveworks Connector with their Jira (Atlassian) account. This all works fine, but after authenticating, the approve and deny buttons no longer work because the information that was stored in them is wiped. Is there a way to work around this so the information in the buttons are not wiped? Or to send another set of buttons to the user after authenticating? Or some other workflow to accomplish this?Here is how the plugin is built..Jira ticket sends information to a Moveworks webhook listener when an approval is required. Plugin is triggered with the webhook and runs a compound action that sends a notification to the approvers about the Jira approval, and also included  are approve and deny buttons to action on

I have the following built-in connectors, and I have no customized connectors yet.ms_graph    Microsoft Graph (built-in connector)msgraph_teams    Microsoft Graph (built-in connector)msteams    Microsoft Teams (built-in connector)And I’m working setting up the following plugin https://marketplace.moveworks.com/plugins/outlook-lookup-availability. However I noticed that I already have the Microsoft Graph built-in connector, therefore I was wondering if I need to set up a customized connector even thought I have an existing pre-built one. Or if I need to configure a customized connector to build the mentioned plugin? The reason why I’m asking this, it’s because am getting different answers when using Moveworks Agent Architect