Tool Studio

Hi all,I’ve hit a few issues with scheduled plugins that make schedules hard to verify and debug.“Start immediately after publishing” behaves differently between my QA and PROD environments, and neither matches the docs. The Scheduled Triggers docs say cron schedules use the Start at time zone first, then the End at time zone, and fall back to UTC if neither is set. They also say that after publishing, “Start immediately” becomes “Start at” with the publish time saved.In QA, the setting stays on “Start immediately after publishing” and never flips to “Start at.” The plugin ran at the expected time last Friday. In PROD, it flips to “Start at” with the publish time, but my time zone is also pre-filled behind the time zone selector. I never chose one, and nothing in the UI said it was set.The flip in PROD matches the docs, but the time zone isn’t mentioned there. Given the documented priority order, a pre-filled time zone would take the place of the UTC default. The time zone picker also

Our organization follows the Sarbanes-Oxley Act (SOX). SOX requires us to follow documented controls and keep proof that required development, testing, review, and approval work was completed.Our SOX process requires developers to:Store code and unit test evidence in GitLab. Include the related backlog card number. add the GitLab link to the backlog card. Connect code comments to an approved backlog item. Store the code in a repository that requires users to sign in. Have a peer or Technical Lead approve each pull request. Developers cannot approve their own pull requests. We build agents in Tool Studio. Moveworks and GitLab are not connected. Our developers must manually copy the code and other development records from Moveworks into GitLab.We want to meet our SOX requirements without creating more manual work than needed. We would like to learn how other Moveworks customers handle this.How does your organization document this work?What Moveworks code or development records do you sav

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. API call fails with "Invalid attendee".# Good — platform handles fuzzy matching, disambiguation, validation- name: attendees descrip

Looking for the latest updates? Visit this guide in the EmployeeWorks product hub on the ServiceNow Community. That’s our primary home for this series and where updates will appear first. Have you ever needed to get something done at work, but had to ask a colleague which system to use or how the process works? We’ve all been there.Employees shouldn’t need to know which system handles their request, jump between portals, or learn how every application works to get something done. EmployeeWorks gives them one place to ask for what they need and work across connected enterprise systems.For us as developers, that experience is more than just connecting to an API. A useful plugin maps the request to valid inputs, calls the right systems and respects business rules. It might sound like a lot of work, but ToolSmith can help us plan and build a plugin from scratch. We’ll do exactly that in this series.Table of contentsIntroduction What is EmployeeWorks? EmployeeWorks tools: when to use plugin

Does Moveworks expose a supported API, built-in Agent Studio action, or Events Workspace integration that allows a webhook-triggered Ambient Agent to send a message to an existing Employee Communications distribution-group audience, using the audience's group identifier rather than individual employee email addresses? 

I am building a use case where on a schedule, I run a call to ServiceNow to gather a list of users that need to fill out a specific form and notify them. The notification has a button for them to trigger a conversation process. That process walks them through providing their options for the slots that will go be used as input arguments for a HTTP call at the end back to ServiceNow to fill the form. There is also a confirmation before sending the HTTP call. The notification is working, the button triggering the conversation process is working and the flow of the conversation to gather the slots seems to be working. It is always failing when sending the HTTP call at the end.When testing, at the end, it prompts all the selections I made properly, I click yes to confirm and then it says there was an issue submitting the form. The issue is that there doesn’t seem to be a way to troubleshoot what happened. When I look at the logs, the HTTP call does not show in the logs. It ends at the notif

HTTP Action throws error code 13121 on Publish in Agent Studio with below trace:Sorry we cannot process your request this time.Error Code: 13121 If the error persists, please contact the support team with the following trace ID - 6ebbcb8d8a6134db53218f88ce4fc4d7

Hi,Is there any workaround to catalog item form fillability for ServiceNow catalog item forms.most of our form are still not fillability due to client scripts.Regards,Rajeev

Hi everyone,I'm working with a Conversational Process in Moveworks Agent Studio and have a slot that needs to capture multiple values from a predefined set of options.Current experience:Bot:Which options would you like to select?1. Option A2. Option B3. Option CPlease reply with one or more numbers. While this works, I'm trying to understand whether there is a more user-friendly approach available in Agent Studio.There should be buttons which user will just select and the job is done or a check box currently user doesn’t want to write the things , so there might be a option to get this thing as a clickable buttons or some sort of UI experience not like bot will give all in text and again I have to write the thingsPlease select the options you would like:☑ Option A☑ Option B☑ Option C☑ Option D What I've Already TriedCreated a slot Used a Static Resolver Enabled list-based values Defined predefined optionsThe resolver successfully restricts valid values, but the interaction still relies

We are trying to establish Connector in Studio Developer to Deltek Costpoint T&E system using JWT authentication. Need guidance to establish this custom connector.

Building enterprise-grade AI assistants today goes beyond chat. It means connecting to the tools people already use, enabling assistants to take governed action, and reducing friction within existing team workflows and processes.  How to do that using the latest platform innovations, including ToolSmith, is exactly what we’ll be exploring at now[dev] 2026.  Across two days, you’ll have multiple ways to explore what enterprise-grade AI assistants can look like in practice:  Hands-on labs: Go from intent to implementation by building tools that search, act, and enforce guardrails across business systems using Moveworks - powering ServiceNow EmployeeWorks.  Ask the Experts: Bring your questions on ToolSmith, MCP, EmployeeWorks, skill steering, specialized assistants, and how the pieces fit together.  Hackathon: Spend the day building with EmployeeWorks, ToolSmith, and ServiceNow tools, then compete for prizes and a chance to be recognized on the main stage.  Vibe Code Lounge: In 15 min

Our team is experiencing loss of work - saves sometime revert 10 minutes later or hours later.  It has been happening for a couple weeks and might have started around the version control addition.  Anyone else experiencing this

Hello,As I saw mentioned previously, Build plugins are custom plugins that you create from scratch or customize to meet your specific needs . These require development work using Agent Studio. My team has identified some Workday use cases that do not fall within those listed as build plugins currently. Are those buildable plugins the only ones we can create and customize, or is it possible to create an entirely from scratch plugin? I’m asking generally speaking at this point. Thanks,  Todd

I am working on implementing/testing the Outlook plugins from the marketplace. They all seem to work individually so far but I seem to have an issue passing from one to another and can’t seem to figure out the issue. If I know a meeting I haven’t accepted and say I want to accept/deny that meeting directly it can handle that straight no issues.If I ask for a list of meetings I haven’t accepted it is able to provide a list but if I then ask to accept/deny a specific meeting from that list it doesn’t seem able to transition to the respond plugin properly. What would be the best way to troubleshoot the context issues here? The logs don’t seem to show the slots properly to determine what isn’t transferring over correctly.

Salesforce Approval Succeeds, but Bot Receives success: false I’m working on a bot integration with Salesforce to allow users to approve or reject JCO requests directly from the bot.The overall flow is:Bot → HTTP Action → Salesforce → Approval/Rejection → Response back to BotThe interesting part is that the approval/rejection itself is working correctly. The action is successfully processed and the status is properly logged in Salesforce.However, when the same action is executed from the bot, the response captured by the bot shows:success: falseThis creates a problem because the bot uses the Salesforce response to determine the message shown to the user. As a result, the bot indicates that the action was unsuccessful, even though Salesforce has actually processed the approval/rejection successfully.What makes this more interesting is that when I test the same HTTP Action directly, using the same type of request, Salesforce returns:success: trueSo the behavior looks something like this:

I am running into an issue with an HTTP connector. I had to update the private key for the JWT Auth. For some reason the API calls when testing in Agent Studio are not going through properly. It’s saying access denied but I have tested this new key via postman to confirm it was set up properly. It seems to be an issue with how the backend is sending the authorization/jwt. When I am in Agent Studio testing the API call I can see the response but nothing in Console even though the option is there. I am trying to troubleshoot this further. Is there any way to troubleshoot these API calls to see what is actually being sent to understand what could be going wrong.   

🚀 Building a Jira Assistant with Moveworks 📌The NeedSwitching between a conversational assistant and Jira to find issues, review details, or add updates can interrupt productivity.We leveraged the OOB Jira plugin capability as a foundation and enhanced it to meet our specific business use cases and user experience requirements.The result is a tailored Jira experience that allows users to retrieve and update Jira information directly through natural-language conversations. 🔧 What We BuiltOur Jira Assistant supports four common scenarios:View Jira tasks assigned to the current user Retrieve details of a specific Jira issue Add a comment to a Jira issue Search assigned Jira issues using keywordsUsers can simply ask:💬 “Show my Jira tasks” 💬 “Show details for Jira PROD-2110” 💬 “Add a comment to Jira PROD-2110” 💬 “Find my Jira issues related to VPN” 🏗️ Solution Architecture User Utterance → Moveworks Plugin → Conversational Process → HTTP Action → Jira REST API → Script Action → Form

We’ve been trying to implement the Submit PTO plugin for Moveworks, but we’re facing a few permission errors. When we start the conversation to submit the PTO Moveworks gathers all the information: PTO type, amount of time and so on but when trying to submit we’re getting the following errors: and also: I’m wondering if this issue is on the Workday side or could it be an issue with the Workday Connector’s Scopes?Is there scopes missing from the Workday Connector or is it something related to Workday configuration itself?

Hi everyone, I’m working on a Moveworks conversation flow where an action is executed with the Confirmation Policy enabled: Require consent from the user before executing this activity.The default confirmation prompt displays some information about the action before asking the user to confirm. However, I have a requirement to display additional fields/details in the confirmation step so the user can review all relevant information before clicking Yes/Confirm.For example, I would like the confirmation screen to show additional details such as: Request/transaction details Additional input fields Dates and times Leave/request type Number of hours Other dynamically generated values Is there a supported way to customize or extend the confirmation prompt/card generated by the Confirmation Policy?Specifically, I’m looking for a workaround or recommended approach to: Add additional fields to the confirmation UI. Display dynamic values from the conversation/action inputs. Allow th

I have a compound action with multiple try/catch statements that is live and currently working. I am trying to add specific status codes to one of the catch statements and it won’t validate but doesnt say why specifically. One thing I noticed is that inputting the status code in the visual editor comes out differently than the documentation shows it should be entered but even when I match the documentation it still doesn’t validate. What could I be missing? This is how it comes out from the Visual Editor 

Hi Team, We are currently performing a POC to connect DocuSign with Moveworks. Our goal is to send proactive notifications to users whenever a new envelope is created in DocuSign for signature.To establish the connection between DocuSign and Moveworks, we explored the available authentication methods. Since the DocuSign platform supports both OAuth and HMAC signature-based authentication, we initially attempted to use OAuth. However, due to certain parameter limitations on the DocuSign platform, we were unable to proceed with that approach and switched to configuring HMAC authentication instead.We have completed the HMAC configuration, but when Moveworks receives events from DocuSign, we are encountering the error shown below.Here is the listener configuration:We can see the same signature in the incoming header, so we're not sure why the verification is still failing. Has anyone experienced a similar issue while integrating DocuSign with Moveworks? If so, could you please share any gu

Encountering the following issues with Agent Studio Quickstart Guide Exercises: 1) Quickstart #3: Basic Process Agent: Not able to generate/view any Purchase Requests in Moveworks Purple API as shown below in the screenshot. Tried creating multiple session IDs, but this step won’t work. Link to exercise: https://docs.moveworks.com/agent-studio/quickstart-guide/quickstart-basic-process-agent  2) Quickstart #4: Structured Data Analysis (SDA): Facing issues with the “Fetch Accounts” endpoint and receiving the following 401 error:Link to exercise: https://docs.moveworks.com/agent-studio/quickstart-guide/quickstart-4-structured-data-analysis-sda  Could any one please help with these topics?  Thank you!-Anand. 

Folks according Claude this should be the price market for consulting companies in the U.S when building customized plugins in Moveworks. Do you guys agree?