Product Forums

 Hey community, Quick update: the Sample Interactions column currently visible in the KB Gaps widget will be removed, to ensure proper governance around access to raw user interactions.Users with the Interactions Viewer role will still be able to click the widget to drill down and view raw interactions in the side pane.This same change will also apply to the Sample Interactions column in Plugin Insights (Forms) starting March13.  

I am getting an error while trying to test a compound action which states  Message: Sorry we cannot process your request this time.Error Code: 13121Trace ID: YTkNgH59WP66ivn2What does this error means ? How to get over this

Hello Community!I wanted to share a set of practical use cases for managing device health that empowers end-users to take action when their hardware needs attention. While these notifications and workflows leverage Nexthink, other device management tools can be substituted using a similar architecture.The Solution: Nexthink Ambient AgentsNexthink offers a Remote Actions API to initiate tasks, native webhooks for real-time alerts, and Nexthink Query Language (NQL) to define data triggers. Combining these capabilities allows ambient agents to listen, notify, and assist users with actions such as:Clear Device/Teams Cache Restart Device

Hi team,I’m trying to enforce a 1MB file‑size limit on file uploads captured through a Moveworks slot. I attempted this using a Script Action, but it appears the approach won’t work because:The location field of an uploaded file is not a valid URL that can be fetched. Script Actions run in a sandbox and cannot directly access Moveworks internal file storage. Because of this, the script cannot read the file bytes or calculate file size, so validation never triggers.I wanted to check whether Moveworks currently provides any supported method or API to validate file size before sending the file to a destination system via HTTP Action.Is there an officially recommended pattern or upcoming feature for this?Thanks in advance for any guidance

Hi everyone,We’re currently building Ambient Agent use cases in Agent Studio and are running into the same challenge mentioned in this thread — there isn’t a way today to access Ambient Agent analytics.While we understand from Moveworks that proactive notification analytics are on the roadmap or that we can use the Data API (we don’t have it setup yet), we’re trying to understand what other customers are doing right now to monitor success and adoption for Ambient Agent use cases in the meantime.For those of you who have Ambient Agents in production:Are you capturing any success or usage metrics? If so, how are you doing it? Using notification logs? Integrating with downstream systems (ex: ticketing platforms, Power Bi dashboard,

Hello Moveworks community, As announced before here, we’ll be updating the SIEM log pipeline on March 31st’2026. Please refer this post to understand the list of enhancements that you can expect.  Let us know if you have queries and we’ll be happy to help. Thanks

Hello,I would like to know if it is possible to add a clickable link for Live Agent Chat inside the Smart Handoff text.Right now, users first choose a team (for example, IT or Finance). Then they choose an option in the second drop-down (for example, “Finance Applications supported by EAS”). After they choose this option, a Smart Handoff text box appears with more details.Today, the Live Agent Chat is shown as a separate option in the drop-down list, and the link is hard coded under each domain. Instead, I would like the Smart Handoff text itself to include a clickable link that will start a live chat with an agent.In other words, when the Smart Handoff text appears (for example, for “Finance Applications supported by EAS”), I would like the phrase “Live Agent Chat” in that text to be a clickable link that opens the live chat.Is this possible to configure in Smart Handoff (for example, by adding a URL or action to the descr

Hey agent builders!Python Actions dropped on this session and the energy was immediate — An attendee hit us with a "no effing way" in the chat before I even finished the sentence. We also shipped a brand-new docs site, rolled out knowledge and form content activities, and then spent the back half tackling pre-submitted questions and a live DSL debugging session that humbled me in real time.Ryan and Steve were both on as co-hosts. Solid crew, solid session. Here's what went down. New Docs Site — docs.moveworks.com We shipped a completely rebuilt documentation site. The old sidebar situation is gone — now there's a product switcher that breaks things into AI Assistant, Enterprise Search, Agent Studio, IT Service Management, and the API Reference. The search is actually useful now: keyword results plus an AI assistant tab that can answer follow-up ques

If you've built anything non-trivial with APIthon, you've hit the ceiling. Complex data transformations, real calculations, text processing — either impossible or painfully hacky in a restricted scripting subset. The most consistent ask from builders has been: "I need real Python with real libraries."Done. Python Script Actions let you write full Python 3 directly in Agent Studio — with access to all built-in modules and a curated set of pre-approved external libraries. They plug into Compound Actions and Conversational Processes exactly like APIthon scripts, but with dramatically more power. Define input arguments from slots or previous step outputs, write your logic, and the value of the last line becomes your output. That's it. What you get:→ Full Python 3 with all standard libraries (json, datetime, re, math, collections, etc.)

If you found an ambient agent on the Marketplace, you already know the pain: there's no install button. You're staring at someone else's fully-built agent and manually recreating compound actions, trigger configs, webhook listeners, and mappings by hand. Nobody was doing that.That's fixed. You can now install ambient agents directly from the Marketplace into your environment in a single flow. Webhook plugins, scheduled trigger plugins — they all install cleanly with all their compound actions and mappings imported automatically. Same process also powers dev-to-prod promotion, so sandbox-to-production workflows are first-class now.What's included:→ One-click Marketplace install — ambient agents now have an Install button. No more manual recreation.→ Automatic asset import — compound actions, trigger configurations, and mappings come along for the ride.→ Smart asset resolution

We want to start building a use case to let users view the required skills for their requested job profile. We have a couple of questions to assess the feasibility for a client. Here are the requirements for reference: Enable employees to do the below via the bot: View required skills for their job profile and  View their most recent skills assessment (self + manager)  View their entire history of skills assessment  View required skills for any given job profile  Show a delta of skills and skill levels between any two job profiles for example, show me the Skills required and the expected skill level for Level 7 Design Release Engineer vs Level 6 Design Release Engineer or between my job profile and Level 7 Designer  Manager can ask and view skills for any employee in t

Is it possible to reference and manipulate a user attribute within a Content Activity? For example: grab a user’s email username@email.com and remove the @email.com so that it returns only username

Hey all,I’m wondering if anyone has tried to connect their Copilot to Responsive (RFP) libraries and has any advice to share? We have a new team joining our Copilot instance that has a huge library of information built in Responsive. We’d like to set this up for Knowledge Base ingestion so the bot can summarise that information in addition to our Confluence spaces.

 Hey team, we are set to roll out an update on KB gaps widgetTo improve the quality of Knowledge Gaps, new logic will only count interactions as KB gaps when Knowledge/Enterprise Search is considered and no other plugin is used (excluding Smart Handoff).With this update, Total interactions metric within each Topic will drop. Overall total interactions across all Topics will reduce by ~20-30%. This is expected, since the widget will now contain more refined KB gaps that customers can rely upon.

Depending on the response to a button in my compound action I need to direct a user to a website, with some parameters attached.I currently wait for them to press the button then display the link but this is an additional step that isn’t really necessary.It would be more efficient if they could click the button and be taken directly to the web page.Is this possible?

We have our bot deployed in MS Teams today. We are looking to enable the ability to upload files to the bot to take advantage of Brief Me. We have everything enabled in Moveworks Setup. However, I’ve looked through the documentation but can't seem to find how to enable the bot’s ability to upload files in MS Teams. Is there a MS Graph permission or is this enabled somewhere else to enable MS Teams to allow you to upload a file?

I wanted to flag a potential scalability observation, and keen to have further discussions.With the introduction of Ambient Agents, more systems are integrating with Moveworks via webhooks. As we continue to add plugins across multiple systems, the volume and frequency of inbound calls will increase significantly, which raises the risk of hitting rate limits (HTTP 429 errors).To illustrate with a concrete example:One Power Automate flow pulls data from Intune and sends device status alerts to Moveworks users. A second Power Automate flow also pulls data from Intune and sends device status alerts to Moveworks users. A ServiceNow flow sends SAM reclamation alerts to Moveworks users.If these plugins are scheduled to run daily, the cumulative execution time becomes quite long. While these jobs are running, additional webhook calls from external systems can still occur, increasing the likelihood of rate limiting.We

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?

Hello,We are reviewing our data retention practices to comply with the General Data Protection Regulation (GDPR). Our internal policy requires us to delete or anonymize user data two years after someone leaves the company.At the moment, the only way Moveworks proposes we do this is to delete all of a user’s prompts from the backend. However, this also removes the related analytics data and affects our usage statistics (number of WAU, number of interactions...) from that period.Is there a way to anonymize a user’s data once they leave, so that it can no longer be linked to them, while still keeping the overall analytics?If not, are there any plans to support this in the future?

 Hi everyone,We are excited to announce a significant upgrade to the Moveworks Search engine. We are transitioning from our legacy Knowledge plugin to the Enterprise Search (ES) plugin. How does Analytics change with the Enterprise Search plugin?The user experience remains seamless, but you’ll notice more comprehensive results and summaries. From "KB Insights" to "Search Insights"Since Moveworks now searches far beyond just your Knowledge Base, we are renaming the KB Insights dashboard to Search Insights.The Data: This dashboard now captures activity from both the new Enterprise Search and the Knowledge Base plugin—whichever is enabled in your org. If both are live, it includes insights from both. Actionable content signals: To keep your “content signals" accurate, Search Insights will on

Brief summary: New tickets often lack context agents need to troubleshoot quickly. This pattern uses a Moveworks Ambient Agent to automatically pull relevant enterprise data at ticket creation time, run LLM actions to correlate + summarize data, and post a single Agent Brief to the ticket before first touch, reducing repeat investigation and accelerating MTTR. IssueNew IT tickets usually arrive with limited context. The agent spends the initial minutes doing repetitive investigation:What changed recently? Has this happened before? Who owns the service? What systems/dependencies might be involved? What’s the best next step?SolutionAutomatically generate one consolidated Agent Brief at ticket creati

When a user asks Moveworks Copilot a question, that prompt gets stored as raw interactions in the analytics in Moveworks admin portal. How long is the raw interaction data available for? If we want to shorten the period, where do we configure this? Thank you.

You can now collect files from users right inside Moveworks! With File Slots, you can design plugins that request and receive files — like receipts, documents, and invoices — and send them directly to external systems.  What's included:• File uploads via a built-in "Upload File" button in chat• 🎕 New: Multiple file uploads now supported via List[File]• Seamless integration with HTTP Actions through flexible file mapping• Supports raw upload, multipart/form, multipart/related, application/octet-stream, and base64 encodingSupported file types: .png, .jpg, .jpeg, .pdf, .txt, .csv, .xlsx, .xlsm, .xls, .xltx, .xltm (up to 5MB each)📖 Learn more:• File Slots docs:

Hello Moveworks Admins,We're excited to announce that Upload Avatar feature will be available for Embedded AI Assistant in the Moveworks Setup on 25rd February 2026. 🎨 What's New?Admins can now upload a custom AI Assistant avatar for embedded AI assistant (prev. MoveworksForWeb) directly in Moveworks Setup. This custom avatar will appear only for embedded AI assistant and will not affect other user-facing experiences such as chat applications, web app and popup forms.📋 Image Requirements:Format: PNG only File size: Maximum 2 MB Dimensions: Up to 1000 × 1000 pixelsIf no image is uploaded, the default Moveworks AI Assistant avatar will be used. 🌟 How to upload AI Assistant Avatar?Navigate to Chat Platforms → Web Chatbot → Desig

I’m facing an issue with a Compound Action where the flow executes successfully until fetching the manager_record, but the notify step does not trigger. There are no errors in the logs, both employee_record and manager_record are not NULL, and the workflow does not explicitly fail or terminate. The execution simply stops after fetching the manager record, and I don’t see any logs beyond that point. For testing, I’m using a single static record via script, but in the actual use case, the data comes from an HTTP action, which is why a for loop is used. I’m also attaching a screenshot of the logs for reference.Here is the exact Compound Action configuration:steps: - script: code: | return [{ "LOGON_NAME": "mw_test_user_5@company.com", "EMAIL_ADDRESS": "mw_test_user_5@company.com", "MANAGER": "manager-name", "ACCOUNT_EXPIRY_DATE": "2026-02-26 0