We've made some updates to the toxicity filter!You can now choose which of five fixed content categories your Moveworks AI Assistant will engage on. The old "Specific Topic Toxicity" model with free-form custom topic exceptions has been replaced.The five categories — all blocked by default:Violent— physical violence Sexual Content or Sexual Acts— sexually explicit content Suicide & Self-Harm— mental health and self-harm topics Unethical Acts— content promoting unethical behavior Jailbreak— attempts to bypass the Assistant's safety instructionsOpt-in to only the categories your organization wants the Assistant to engage on. Uncheck at any time to return a category to being blocked. Selections apply to every future interaction.A common reason to allow a category: Allowing Suicide & Self-Harm lets employees asking for mental health support get routed to your EAP knowledge instead of receiving a generic decline.Where to configure Chat Platforms → Display Configurations → Moveworks AI Assistant Display Settings & Disclaimers → Safety Guard: Allowed Content Categories  To verify your settings are working                         After saving, test directly in your Moveworks AI Assistant:                                                                                                                            - Send a message that falls into a blocked category — the Assistant should decline and return a refusal message.  - Send a message that falls into an allowed category — the Assistant should respond normally.    Note: Changes may take a few minutes to take effect after saving.A few things to knowThis is the Moveworks-specific safety check. Underlying OpenAI/Azure toxicity protections still apply and aren't configurable here. Align with HR, Legal, and Security before allowing any category — selections apply to every user in your org.Read how to configure the Toxicity filter here.

Starting May 1st, the standalone API Audit Logs page in Moveworks Setup will be retired. All API audit log data is now captured within the new Built-in Plugin Logs view, available under Organizational Details → Audit → Built-in Plugin Logs.What's changingYour existing API audit logs — request/response payloads, HTTP status codes, method types — are now available in Built-in Plugin Logs under the log type action.http.trigger. Earlier data from the API Audit Logs page has also been carried over, so there's no gap in visibility.What's not changingThe data itself. Everything you relied on in API Audit Logs is captured in the new view. The only difference is where you access it.What you need to doNothing. Just start using Built-in Plugin Logs in place of the API Audit Logs page before the May 1st sunset.What else you getBuilt-in Plugin Logs goes beyond API calls. You also get workflow execution logs (ticket_gateway.*), trace IDs to follow a plugin execution end to end, and filters for log level, plugin, requestor, API method, status code, and more. This was announced on April 20th and is now live for all customers.  Link to announcement of built in plugin logs :  For full details, see the Built-in Plugin Logs documentation.

Hey Community!We wanted to announce that the we are about to deprecate the old legacy interactions table on May 20th. Post 20th May, View interactions button will take you to the new interactions table as marked on the diagram below.   

Hello Moveworks Community.In January, we announced a major Search upgrade - the introduction of the new Enterprise Search plugin, starting with a rollout in the US and EU data center regions.We have been working on bringing the improvements and enhancements to all of you in every region (see our previous update post here if you are interested), and we are ready to enable these updates next week!Rollout timeline updatesThe search enhancements will be rolled out across regions as follows:US & EU : All remaining US and EU customers on Tuesday, 4/28. CA : All CA customers progressively starting Thursday, 4/30 and concluding by Wednesday, May 6. AU: All AU customers progressively starting Thursday, 4/30 and concluding by Wednesday, May 6. GovCloud : All GovCloud customers progressively starting Thursday, 4/30 and concluding by Wednesday, May 6.What's changing As previously shared, we're migrating AI Assistant to a new Enterprise Search (ES) plugin with an upgraded, scale-ready search and relevance system.Why / the benefitsThe new plugin can search across millions of documents, delivering more relevant answers for your employees. This upgrade also delivers better relevance quality and more reliable results for all non-English speaking users. Employees will automatically see results prioritized for their locale and query language with no special setup required. It simplifies how language and geo controls work, rather than admins manually configuring boost settings and users having to explicitly set a preferred language, both become native ranking signals.What do admins need to know? No action required. Existing manual language and geo boost settings will no longer be needed. These controls will be retired as part of this update as both will become native ranking signals.Change to end-user experience Users will notice more relevant results and broader content coverage. Results will automatically uprank content based on the user's language and location, while not eliminating relevant content across other languages. No changes needed from employees. Users may occasionally see relevant results in a language other than their preferred language.Also coming soon: Multilingual document search In addition to that, we are excited to share the upcoming support for searching for non-English files in AI Assistant and Enterprise Search. Check out the post on this here.

We've shipped a new log view in Moveworks Setup — Built-in Plugin Logs. You'll find it under Organizational Details → Audit → Built-in Plugin Logs. What is this?Built-in Plugin Logs give you visibility into the external API calls that Moveworks built-in plugins make to your integrated systems, along with workflow execution logs. This covers calls like creating tickets, provisioning software, unlocking accounts, adding comments, and more — plus the workflow steps that lead to those calls.The view captures two types of logs:External API call logs (action.http.trigger) — the actual HTTP requests and responses between Moveworks and your external systems. Workflow execution logs (ticket_gateway.*) — ticketing workflow steps such as which workflow was identified, which actions were triggered, and the final execution result.What you can do with itEach log entry includes a log level (Error or Info), timestamp, trace ID, log type, plugin name, requestor email, and a summary. Click any row to open the full detail panel with request and response data.The trace ID is key — all log entries from a single plugin execution share the same trace ID, so you can trace from the workflow identification step through to the API call and its outcome.Filters are available for time range, log level, trace ID, log type, plugin, requestor, API method, and API status code.What about API Audit Logs?If you've been using the standalone API Audit Logs page, those same external API call logs are now captured here under the log type action.http.trigger. Same data — request/response payloads, HTTP status codes, method types — just within this unified view.We will be sunsetting the standalone API Audit Logs page on May 1st. No action needed — just start using Built-in Plugin Logs going forward.Key notesLogs are captured on a forward-looking basis. Historical data is not backfilled. Logs are retained for 1 week on a rolling basis. Authentication API calls are not recorded to avoid exposing credentials. A single user action can produce multiple log entries — Moveworks plugins may call the same API more than once, depending on the workflow, and automatic retries are surfaced as-is. Access is governed by the PII Viewer role. All Setup users can see the log table, but only Super Admins and PII Viewer role users can view unredacted request/response details.ResourcesBuilt-in Plugin Logs documentation

Why this mattersWhen the AI Assistant delivers an unexpected response, the first question is always why. Until now, answering that meant filing a support ticket and waiting for Moveworks to investigate. Chat Playback puts that diagnostic power directly in your hands.What's newAI Assistant Chat Playback is a troubleshooting tool in Moveworks Setup that lets you replay any user conversation and inspect the assistant's reasoning process step by step. Paste a conversation ID and see exactly how the assistant processed the request across four stages:Intent — How the assistant interpreted and reformulated the user's query. Compare the original message against the rewritten query to spot misinterpretations. Plugin Selection — Which plugins were available to the user and which ones the assistant chose as relevant. Plugin Execution — What arguments were passed, what resources were returned, and whether execution succeeded or failed — including specific error codes. Response Generation — Which resources were cited in the final response, and where they came from.This makes it straightforward to pinpoint whether an issue originated from intent misinterpretation, plugin selection, a downstream execution failure, or a citation relevance problem.AvailabilityChat Playback is live today for partner-managed orgs. It will be enabled for all orgs by April 27.Key NotesAccess is role-gated. Chat Playback displays sensitive conversation data. Only Super Admins and users with the PII Authorized Viewer role can access it. Conversation ID required. Playback is scoped to a single session — you cannot search by user email or browse conversation histories. This is by design for privacy. All access is audit-logged. Every lookup is recorded with the accessing user, conversation ID, and timestamp for compliance review. Transcripts available after ~3–4 hours. Conversations need time to process before they appear in Chat Playback. Action plugin failures? Copy the Trace ID from the reasoning panel and look up the full error chain in API Audit Logs for the downstream API call details.ResourcesAI Assistant Chat Playback documentation Built in plugin logs documentation 

Update: We've upgraded the AI models powering LLM Actions in Agent Studio. Here's what you need to know.What changedGPT-4o and GPT-4o-mini have been retired by OpenAI and are no longer available. All existing use cases that referenced these models have been automatically upgraded to GPT-4.1 and GPT-4.1-mini, respectively. Your agents continue to work with no interruption.Do I need to do anything?No. The migration has already been applied. Your agents are running on the updated models today.If you're creating new LLM Actions or updating existing ones, select a model from the GPT-4.1 family going forward. GPT-4o and GPT-4o-mini will no longer appear as options.How Moveworks handles model upgradesAs a managed AI platform, Moveworks monitors model availability across providers and handles migrations so you don't have to. When a model is deprecated, we upgrade affected configurations to the best available replacement -- keeping your agents running without manual intervention.We're also evaluating ways to simplify model selection in LLM Actions in the future, so you can focus on the reasoning capability you need rather than tracking specific model versions based on dates.Questions?If you have questions about how the model change affects your agents, or want to understand which model your use cases are running on, reach out to the Moveworks team. Thank you!

We’re excited to announce major upgrades to content troubleshooting in Moveworks Setup, available starting April 15, 2026. This release enhances visibility, accuracy, and usability across the Data Crawling Viewer and Control Center, making troubleshooting faster and more effective.🧭 What’s New in the Content Troubleshooting Enhancements?Data Crawling Viewer Enhancements More accurate crawl statuses: Improved logic to better reflect crawl outcomes, eliminating misleading success/failure states. Crawled Records view: Records successfully fetched during a crawl run, shown with record ID, title, and timestamp. Failed Calls view: API calls that encountered errors during the crawl, including: Error code (e.g., 401, 403, 429, 500) Error message explaining the cause API endpoint that was called when the failure occurred Redesigned UX: New Healthy/Unhealthy resource statuses, a dedicated View Logs page, cleaner UI, and consolidated content resources in one section. Redesigned UI/UX and New Healthy/Unhealthy Crawl HealthCrawled RecordsFailed API Requests Control Center Enhancements Record Activity Logs (New): Record-level visibility into processing and enrichment events and errors. Terminology update: "Serving / Not Serving" is now "Indexed / Not Indexed" across all labels, widgets, and tables to accurately reflect the status of content. Crawled  Table Improvements Content Status → Indexed / Not Indexed (previously: Serving / Not Serving) Permission Status → Indexed / Not Indexed (previously: Permission Crawled = true/false, which did not indicate indexing status) ServiceNow User Criteria support: ServiceNow user criteria (KB permissions) now show Indexed / Not Indexed (previously: Not Applicable) Record Activity LogsControl Center Enhancements ⭐️ Key BenefitsWith these enhancements, Moveworks admins can effectively troubleshoot content-related issues directly inside MW Setup:More accurate crawl statuses — eliminates misleading success/failure states for more accurate assessment of crawl runs. Crawled Records view — confirms which records were fetched from the source system during a crawl run. Failed Calls view — surfaces the exact API call that failed with the error code and message, helping identify issues such as permissions, authentication, rate limits, or source system errors. Admins can investigate further by copying the API request and executing it in API Playground Record processing logs — provide visibility into record-level processing and enrichment steps to help diagnose why records fail to index. Indexed/Not Indexed terminology — shows whether a record is in the index and available to be served to users, making it easier to troubleshoot content availability.✋🏻CalloutsData Crawling View Failed call counts are not available for Forms, FAQs, and Users API request details may not be available for all systems. However, they are supported for Enterprise Search systems Failed call count ≠ records not fetched — a single failed call (e.g., at a folder level) can affect multiple records. Some Moveworks-imposed errors may show an empty error code. Common causes: record exceeds size limit, download timeout, missing/invalid attributes, or empty content body After this change, data prior to March 15 will no longer be available Control Center Enhancements Record Activity Logs show only a subset of processing and enrichment steps. In some cases, all visible steps may show success, but the record may still fail due to issues in other enrichment steps that are not currently surfaced – contact the Moveworks Support team with the record details for further investigation Errors in Record Activity Logs are only surfaced for data from April 1 onward

Get the latest on the product releases and roadmap updates to stay up to speed on all the exciting new features our teams are working on! Roadmap plans and any forward looking statements are shared under NDA and subject to change without notice.We also encourage you to check out the product roadmap for upcoming releases and monthly release notes for details on past product updates. AI AssistantUX Enhancements: Text Streaming - Coming April 29Users will experience natural feeling responses that gradually unfoldUX Enhancements: Slack - Coming June 2026Users will be able to get help, view references, and rate the Assistant as helpful/not helpful all within Slack.GPT 5.2 Update - Live for Standard/Frontier TiersUsers on the Standard/Frontier Tiers have moved to GPT 5.2.World Knowledge App - Coming on April 29 for Customers on EmployeeWorks & Standalone SKUs onlyUsers can now get real-time answers, upload files, and ask questions with World Knowledge all through Assistant on Web.Agent StudioUser Consent Auth - Coming April 30Users have an improved experience connecting AI Assistant to third-party appSharing & Permissions - LP Coming April 30Admin users now have control over which plugins and connectors users view, edit, and launch.Agent Architect V2 - Coming Q2Agent Architect V2 aims to serve as an intelligent co-pilot for building in Agent Studio, which allows developers to focus fully on the business intent while the Architect handles the implementation details on the Agent Studio platform. It strives to accelerate the time it takes developers to build working plugins.MCP Workspace - LP Coming May 29Users can now connect any MCP-compatible server and instantly surface those tools inside the AI Assistant without building additional pluginsEnterprise SearchEnterprise Search Plugin MigrationEU: All customers enabled on April 7 US: Progressive rollout starting April 7 and completing April 15 AU, CA, & GovCloud: Timeline to be confirmedCommunity post and subsequent updates can be found hereVetted Answers - Coming SoonNote: Vetted answers is compatible only with Enterprise Search pluginUsers can now identify if sources are vetted by the “vetted badge”.Multilingual Document Search - LP Coming April 15Note: MLS Knowledge Base rollout is coupled with Enterprise Search Plugin Migration. Users can now search for documents in different languages without translations. Community post can be found here.Rollout Audience Configuration - LiveUsers can now control who can search content surfacing from each connector.Auto-trigger Ingestion on Config Change Detection - LiveWith this update, when the platform detects a config change in Setup, it automatically buffers & dedupes the changes, conducts discovery & deletion of the dupes, and triggers a full ingestion.Moveworks Setup Left Nav & Connector Renaming for Enterprise Search - LiveWe have streamlined the navigation labels to improve the user experience. Read more about it here. Old Left Nav   Updated Left Nav   Connector Display Name Changes Old Names   New Names   Two Content Handling Improvements - Coming Soon on April 15Disable serving content deletion on config removal Users experience improved configuration deletion behavior. Now when a configuration is deleted, content stops being served immediately and triggers indexed content deletion SharePoint cursor handling SharePoint Group APIs sometimes return Token Decoding errors during long running Group Ingestions. This is in progress and we plan to resolve these by retrying the specific groups where we notice these errors. Self ServiceConfiguration Change History - LiveUsers can now audit changes made to configurations and compare changes across versionsAdvanced Configuration Editor - LiveUsers can now use the JSON editing interface to duplicate configs, promote, across environments, make bulk edits, in one go, and more.Configuration Delete - Coming April 30Users can now delete unused content ingestion configurations inside of Enterprise Search, Ticket Workflows, and Rich Ticket Forms.Enhanced API & Service Logs - Coming April 30Users now have deeper visibility into API & Service logs allowing for better troubleshootingAI Assistant - Chat Playback - Coming April 30Users now have access to a secure debugging and observability tool that enables customer admits to playback employee-Assistant conversations.Identity V2 - Coming SoonUsers can now ingest users from external systems in minutesPartner Developer Instances - Coming April 30Partners will now be able to create bulk instances, bulk invite users, share pre-loaded skills with users, and more. Nominate your organization for our Limited Preview ProgramsConsult our list of available Limited Previews here. 🚨Important NoteFeature timelines are subject to change due to various underlying factors. Please check in regularly for timely updates.Thank you for being part of our community! If you have any questions or feedback, please feel free to reach out here.

 Hello Moveworks Community, we're introducing Configuration Delete in Moveworks Setup — a new capability that lets you remove configurations you no longer need, directly from the UI, without contacting Moveworks support. This is available for: • Enterprise Search configurations• Ticket Workflow configurations• Rich Ticket Filing (RTF) configurationsWhy we built thisUntil now, removing configurations (Specifically Enterprise search) required multiple manual steps, coordination with the Moveworks team, and often a long wait for data cleanup to fully complete. For RTF and Ticket Workflows, there was no delete option in the Moveworks Setup UI— making ticketing migrations and general configuration hygiene harder than they needed to be.How it works• Enterprise Search: Deleting a configuration automatically marks all ingested content as non-serving, triggers a full data purge (completes within 24–72 hours), and removes dependent configurations like resource permissions. No extra steps required on your end.• RTF & Ticket Workflows: You can now delete these directly from the Setup UI using the new ticketing configurations journey — making ticketing migrations and stale configuration cleanup straightforward.What to know before you delete• Deletion is irreversible:  To restore a deleted configuration, you’ll need to complete the full setup process again. Review the confirmation warnings carefully before confirming.• User Identity configurations are not removed:  Deleting an Enterprise Search config does not affect user permissions or identity configurations. • Dependency checks are enforced:  If a workflow is referenced in a routing condition, or a form is used in a Smart Handoff, the system will block the deletion and guide you to resolve the dependency first.• All deletions are fully logged in Config Change History (under Troubleshooting Hub) and SIEM logs.This option will be available on 13th April across all regions  For full details and step-by-step instructions, check out the documentation here

  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 Where to find AI Assistant analytics dataTo ensure your team has uninterrupted access to the insights you need, please transition to the following alternatives  : For daily_user_roster: Utilize the /users entity within the Data API. For daily_triage_record: Use the Triage Insights Dashboard and the "View Tickets" download functionality. For all raw data related to the AI Assistant, we recommend utilising the Data API for automated ingestion or our AI Assistant Dashboards for visual analysis. Transitioning to the Data API provides significantly more granular visibility into AI Assistant performance and user engagement than legacy SFTP methods.Support & DocumentationPlease refer to our AI Assistant Analytics Product Documentation for detailed walkthrough on available AI Assistant Insights and data_api setup instructions. If you have additional questions regarding this deprecation or the Data API configuration, please reach out to your CSM.

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 (learn more about the technology).After April 30th, we will upgrade your Triage instance, if you are currently on Triage 1.0.Where can I review the training results?In Moveworks Setup, go to “Triage 2.0” → click on the Config name, e.g. “assignment_group”Then, click “Build Triage Index”Last, click “Fetch Report”. You can also click “Triage Data Visualization” to view the scatter plot of your data.Want to enable Triage 2.0 right now?In Moveworks Setup, go to “Triage 2.0” → switch “Enable Triage 2.0”Have questions about the upgrade or what to expect in 2.0? Drop a comment below and let’s chat! 💬

We’re excited to announce the refreshed product roadmap! We made some updates to the product roadmap and wanted to share what changed and why. We kept hearing that customers wanted better visibility into what Moveworks is working on, so we took that seriously. The roadmap now has a cleaner layout, tooltips and a legend so the icons actually make sense, and reorganized product areas that are easier to navigate.Our goal is for this to be a real, living source of truth.That being said, timelines here are subject to change. Things can and do change, and we'd rather be upfront about that than overpromise. We'll keep the roadmap updated as our plans evolve.Note: Items in Planning may show the current month as their target release date. This can mean one of two things:The item is small enough to move quickly through our development stages and ship within the month The target date hasn't been updated yet to reflect a more accurate timelineWhere possible, we default to the first — shipping sooner rather than later.If you have questions about a specific item, feel free to reach out and we’re happy to clarify. Refreshed Roadmap ExperienceTooltip that shows up when cursor hovers over down arrowTooltip that shows up when cursor hovers over lightbulb icon 

Good news: Upgrades to Moveworks Agentic Reasoning Engine just got a lot more predictable.Introducing the Model Upgrade Program: a new way to get more visibility and control into when your Moveworks AI Assistant receives planned updates to the reasoning engine. This program gives every customer clear upgrade timelines.As a customer, you will fall into one of three tiers in this program:Frontier: You’ll get the latest models as soon as they're available (pre-GA). Best for organizations that want to stay on the cutting edge. This is the default for dev/sandbox tenants and partners. Standard: This is the default tier for most customer production environments. You will receive models once they're in GA. Basic: In this tier, you’ll automatically upgrade at the deprecation deadline, typically 2–4 weeks after Standard. Best for teams with extended change management cycles.What's changing today: Starting April 2, all Frontier and Standard customers will be upgraded to GPT-5.2 — automatically, no action needed. GPT-5.2 brings more comprehensive tool calling and a better enterprise search experience. Read more in this community post and blog. Known issue: Some customers may notice more verbose tool usage explanations and reasoning trace leakages. We’re on it — follow updates here.Want to know what model your tier is on today? Check out this help doc to track which latest model each tier is on.Want to check or update your tier? Go to Moveworks Setup > [Core Platform] AI Assistant > Advanced Settings > Conversation Settings — Model Upgrade Program Tier. If you are having issues with this upgrade and need technical help, please contact Moveworks Support.If you have questions about your tier or the program overall, feel free to add a comment here or contact your CSM, we’d love to help.

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 make maximum out of this new data you must update your data pipeline. Conversations Entity: The scope is moving from "user-engaged" to all conversations, including those initiated by the system. You will now see records for every notification or interception event the moment they are triggered, regardless of whether the user clicks or responds. Interactions Entity: Every proactive message sent by the bot (like a laptop refresh nudge or a ticket update) will now be visible as a bot-actor interaction. Plugin Calls & Resources: We are now capturing the background work! Any plugin calls triggered by system events (like fetching a ticket for an interception) will be recorded, along with the resources used. We will soon be updating our API documentation to capture the exact updates. Important Details With great data comes great volume! Here is what you can expect starting week 1 April , 2026:Entity Expected Volume Increase Key Change Conversations 7-8X increase Includes all system-initiated events. Interactions 5-6X increase Captures all proactive bot messages. Plugin Calls ~25% increase Includes calls triggered without user input. Plugin Resources ~10% increase Includes resources used by automated calls.  Note:These changes are "forward-looking" only. Historical backfills for these system-triggered events prior to go-live, are not possible. Since the volume is expected to grow tremendously, we are implementing a 30 day TTL for Data API. This means that going forward, Data API will allow you to ingest data only up till 30 days back How to Prepare ? Review Downstream Pipelines: Because of the significant volume increase, ensure your ingestion pipelines and storage are ready for the extra rows. Update Your Dashboards: Start planning how to use the new type and detail fields to report on notification engagement and bot proactivity. Check the Docs: We will be updating our external documentation and release notes as we get closer to the launch date. We can't wait to see the insights you unlock with this new level of visibility! 🚀

Hello Moveworks Community, We've introduced a new power tool to Moveworks Setup: the Advanced Configuration Editor. Available under Troubleshooting Tools in the left nav, it lets you view and edit Moveworks Setup configurations directly in a JSON mode — giving you full control without the constraints of the standard UI. What you can do with it:Bulk operations — paste in 150+ destinations or payload mappings in a single save Configuration duplication — copy an entire config from one instance and paste it into another, tweaking only org-specific fields.  Environment migration — promote configs from sandbox to production by updating just the environment-specific values UI fallback — bypass overly strict UI validations that might otherwise block a go-liveA few things to keep in mind:This tool is intended for partners and advanced users — it modifies live configurations directly, so use it with extreme care Standard UI validations and DSL hints are not enforced in JSON mode, which can lead to incorrect DSL and Bender fields - Use with extreme care Secrets are masked and should not be edited through this view.  Only a vetted subset of configurations is available in the dropdown. The configuration names are granular and will not match configuration names present in the Moveworks Setup left-nav. Please refer to the mapping table in the help documentation and find the relevant configuration name. To get started, head to Moveworks Setup → Troubleshooting Tools → Advanced Config Editor. Full documentation, including a reference list mapping Setup nav pages to config names, is available here.

 We're excited to announce Configuration Change History, now available in Moveworks Setup under Advanced Tools → Troubleshooting Apps → Configuration Change History. 📋 What Is Configuration Change History?Configuration Change History gives you complete visibility into every configuration change made in your Moveworks environment. You can see exactly who changed what, when, and compare the before and after versions side by side. ✨ Key FeaturesTime-range search — Filter changes by date range (defaults to last 2 days; supports up to last 30 days) Configuration filter — Search by specific config name, or leave empty to see all changes across your environment. Please note that these configuration names are at the page level and will not directly map to the Moveworks Setup left-nav tab. Use this table to find the relevant Configuration Name in the drop-down.  Version history table — Timestamp, config name, version number, change type, and the user who made the change JSON diff view — Click any entry to see a side-by-side comparison with added, removed, and modified fields highlighted Full attribution — The User column shows the email of whoever made the change, whether that's your admin team, a partner, or Moveworks.  🚀 Common Use CasesScenario How It Helps Something broke after a change Set your time range to just before the incident, scan for recent changes in configurations, and identify what was changed and who made the change Preparing for go-live Audit recent changes to confirm everything was configured as intended Unexpected bot behavior Pull up the relevant config and review its change history for a timestamped answer Compliance or access review Document who made changes and when to support internal audits Verifying partner-led changes Confirm exactly what was modified after an implementation  📖 Learn MoreFull documentation, including a complete Configuration Name Reference : https://docs.moveworks.com/service-management/moveworks-setup/troubleshooting-hub/config-change-history 

We're excited to announce more powerful, upgraded Multilingual Support (MLS) capabilities coming to Assistant and Enterprise Search!Today, via the Knowledge Search (KS) plugin, Moveworks supports non-English search for Knowledge Base Articles (KBAs) by converting both non-English queries and non-English KBAs to English in order to process them. While this approach provided multi-language support, it introduced risk of accuracy loss along the way. Additionally, non-English search is currently not supported for files.With our upgraded, native MLS capabilities, we will support non-English search for files along with KBAs. We’ll eliminate the "double translation" approach entirely, leading to improved accuracy and reliability. Our new upgraded search capabilities, powered by next-generation retrieval and ranking models, work directly over content in its original language across 30+ languages, delivering better relevance quality and more reliable results.We'll also simplify language and geo controls with this upgrade. Today, admins must manually configure language and geo boost settings, and users must explicitly set a preferred language for it to influence results. With enhanced MLS and the new Enterprise Search (ES) plugin (more details here), both become native ranking signals in the core stack, which means employees will automatically see results best matched to their locale and query language without requiring manual configurations. You will still be able to interact with Assistant in 100+ languages as you do today.In late Q2, we'll further enhance user control by replacing today's "preferred bot response language" with two settings that apply across Assistant and Search:App Interface Language: Sets the language of the UI (navigation, controls, labels), independent of what language a user types. Response Language: Sets the default language for responses, employee communications and notifications. Regardless of this setting, users can interact in any language and the experience will respond in the language used for that interaction.We'll also display citations in the source’s original language, with the option for users to translate them into their query language when needed. Refer to the table below for a comparison of current and future state.When will this MLS upgrade be available?Early access to new MLS capabilities will be available starting early Q2 onward, with general availability starting mid-late Q2.Get early accessIf you'd like to try upgraded MLS capabilities ahead of the general rollout, please fill out this form to register your interest for early access. Reach out to your account team with any questions.Functionality Current State: KS plugin Future State: ES plugin + MLS Non-English content search KBAs: supported ✅ Files: not supported ❌ KBAs: supported ✅ Files: supported ✅ Admin controls on geo/language relevance Three admin-configured controls for geo + language Admin boost controls removed; geo/language handled natively via ranking signals Geo handling Two admin controls: Geocode Boost (KBAs) + File Search Geocode Boost (Files) with Disabled/Soft/Hard Geo becomes a ranking signal (no hard/soft settings) Language handling One admin control: Language Boost with Disabled/Soft/Hard Language becomes a ranking signal (no hard/soft settings) Retrieval and ranking language handling Double translation of non-English queries and non-English documents Retrieval and ranking done natively in original languages Query/response language handling Assistant understands all languages, but will respond in the bot preferred response language if it’s set Scenarios: • English users can only see English sources in the response, no matter what settings • Spanish users may see English and/or Spanish sources in the response, depending on the setting Assistant understands all languages and will respond dynamically in the user’s query language regardless of user-set response language Scenarios: • English users will primarily see English content if it exists, but may also see Spanish (or Chinese) sources in the response • Spanish users will primarily see Spanish content if it exists,  but may also see German (or Chinese) sources as part of the citations in the response User preferred language (coming in late Q2) Users can set their own bot preferred language through Assistant; admin-default used if not set User can set two language settings: UI and preferred response; admin-default used if not set Citations display language (coming in late Q2) Citations are shown in the bot preferred language, either natively or translated on-the-fly Citations are shown in the original content language, with an option for the user to translate to the query language

OpenAI recently released GPT 5.2, and we're excited to share that we've been hard at work evaluating it before bringing it to you. We ran a full assessment across a range of the latest large language models and put GPT 5.2 through extensive internal employee testing.More comprehensive tool calling. GPT 5.2 is more comprehensive in the sets of tools it uses to help answer user questions. As a result, it provides a more helpful answer, and is less likely to need to handoff users to internal help channels.Better Enterprise Search. GPT 5.2 works better with Enterprise Search. GPT 5.2 provides a more concise and relevant search query when using Search. This means the assistant finds what you're looking for more efficiently, with less noise in the search process.Stronger Tool Call Post-Processing. After a tool or plugin is called by GPT 5.2, it does a better job of writing code to analyze and restructure the results.Less Hallucinations. GPT-5.2 does a better job of discerning what capabilities it does and doesn’t have and hallucinates less when conversing with the userWhen will GPT 5.2 be available in Moveworks?As of March 9, we have started rolling out GPT 5.2 to customers. These are our target GA dates below: Region Target GA Date for GPT 5.2 in Reasoning Engine United States Wednesday April 1, 2026 Europe Wednesday April 1, 2026 Canada Wednesday April 1, 2026 Australia Wednesday April 1, 2026 GovCloud & Azure-only Orgs Wednesday April 1, 2026 🚧 Is there anything I need to do for this rollout?This change will be made to your AI Assistant during this time period. There’s no additional setup work for this upgrade, nor downtime.🛑 Are there any known issues?Updated April 2: Verbose tool responses & reasoning traces. When your Assistant executes a tool, GPT-5.2 is more likely to explain how it interpreted the results, sharing details about how your tool is structured rather than answering the question. We are working on a fix and will update when resolved. You can course correct for verbose tool responses by influencing the Reasoning Engine through display_instructions_for_model (docs)

Get the latest on the product releases and roadmap updates to stay up to speed on all the exciting new features our teams are working on! Roadmap plans and any forward looking statements are shared under NDA and subject to change without notice.We also encourage you to check out the monthly release notes for details on past product updates.Agent StudioStabilizing Ambient Agent - LiveUsers can now trigger Conversational Processes (CPs) via Compound Actions (CAs) without publishing them as standalone conversational pluginsOptional Slots - LiveUsers can now separate out required inputs from optional context enabling richer, multi-path workflows.File Slots - LiveUsers can now allow plugins to collect and upload files directly in chatKB & Content Activities - Coming on February 26Surface the right knowledge or collect the right information at the exact moment it’s needed.Python Actions with SDA - Coming in MarchUsers can now run Python scrips inside Agent Studio workflows. SDA now supports payloads up to 100MB, giving users more room to generate Python code and analyze plugin responses and datasets without size limitations. Self ServiceDecoupled Indexing and Live Search Configuration - LiveUsers can now individually configure indexing and live search for Unified SharePoint and OneDrive NG ConnectorCustom URL Configuration - Coming February 2026Users can configure custom view URLs for content ingested from ServiceNow and ConfluenceDefine Rollout Audience for a Connector - Coming February 2026Admins can specify a list of end-users who will be able to access ingested content from a connector for testing before global rollout Nominate your organization for our Limited Preview ProgramsConsult our list of available Limited Previews here.  🚨Important NoteFeature timelines are subject to change due to various underlying factors. Please check in regularly for timely updates.Thank you for being part of our community! If you have any questions or feedback, please feel free to reach out here.

Hello Moveworks Community.In January, we announced a major Search upgrade - the introduction of the new Enterprise Search plugin, starting with a rollout in the US and EU data center regions, and enabled opt-in early access. Thanks to everyone who tried out the new plugin in early access! Early feedback has been positive for the experience, including more comprehensive answers and citations. Update to rollout timeline: Progressive rollout starting Tuesday, March 3 over the next 8 weeksWhy: We have been gradually onboarding a few early adopter customers, and carefully analyzing how the new search services are scaling with hundreds of thousands of new users. Our goal is to progressively scale up our infrastructure with the rollout to make sure that all users have a great experience as they are onboarded.We will monitor the performance and will move faster as soon as we are confident that we are well set up to manage the scale.What happens next for US customers?We will be progressively rolling out access to all customers in the US region over the next 8 weeks, starting March 3. This is a longer timeline than we had initially communicated but based on our analysis, we decided to progressively scale up our infrastructure with the rollout to make sure that all users have a great experience as they are onboarded.We will reach out with an email to you when we are ready to onboard you, via switching your organization's search plugin to enterprise search plugin. You will have at least 1 week's advance notice before we make the change. If you are interested in making the switch earlier, please let us know and we will try to onboard you sooner!What happens next for EU customers?EU Rollout Update (March 11): We are starting our rollout in the EU on March 17, and expect to complete it by Wednesday, March 25. Please post any questions in this thread and we will respond ASAP! Thank you for your support of this upgrade. We are excited to bring this experience to everyone!

We’re excited to announce Initiative Designer, now available on the AI Agent Marketplace. Your automation backlog isn't a prioritization problem. It's a starting problem.You know what processes are broken and you know what should be automated, but you may not always know where to begin or how to turn "we should automate expense management" into an actual, enterprise-ready solution.Initiative Designer helps you translate an idea into a structured, business system-centric plan.How It WorksLogin to the AI Agent Marketplace Highly recommended to share and save your progress In the nav bar, head to to “Create” —> “Initiatives” Click on “Generate” and describe the workflow → e.g., "Automate our expense management process. An employee submits an expense, and if it’s under $50, within policy, and includes a valid receipt, it’s automatically approved and reimbursed, but higher-value or out-of-policy expenses are routed to the manager with a request for justification before payment is processed." We recommend providing as much detail as you can about your bespoke business process to generate the best results AI maps the process → actors, tasks, dependencies, bottlenecks Customize → View the output and customize it to meet your bespoke business needs, add or remove steps, specify your specific systems — all in natural language Build → save or share the Initiative link and turn the business process blueprint into real automation using Agent StudioWhat It DoesInitiative Designer takes any workflow you describe in plain English and designs a complete automation blueprint you can build from.What you get:Actors and swim lanes – who does what, and when Task sequences with handoffs – how work flows between teams Pain points at each step – where things break today System integrations – auto-suggested from your tech stack (ServiceNow, Workday, Okta, Salesforce, and 120+ connectors) Try Initiative Designer   

Hello Moveworks Admins,We're excited to announce that Permission Checker will be available in the Ingested Knowledge and Files screen on 21th January 2026.🔍 What is Permission Checker?The Permission Checker tool allows Moveworks admins to verify whether a specific user has access to specific knowledge base articles or files by selecting or providing a user’s email address. 🌟 When to use Permission Checker?A user complains that they cannot find information from specific KB articles or files in their search results, even though they should have access Admins have changed permissions, group memberships, or ACL rules in source system and want to confirm they are reflected in Moveworks After updating permission rules in Moveworks, admins need to validate that content permissions are reflected correctly Need to verify that new employees/UAT users can access expected content records Admins want to audit that sensitive HR, legal, or financial documents are only accessible to authorized personnel and not exposed to unauthorized users👉🏻 How to access Permission Checker in Moveworks Setup?To access Permission Checker in Moveworks Setup:Navigate to Moveworks Setup In Enterprise Search left nav section, expand Enterprise Search → Answers → Ingested Knowledge Select Internal Knowledge or Files screen Click on any record in the table View Permission Checker Tool   📘 Learn MoreFor detailed guidance on using Permission Checker, refer to our help documentation sections:Ingested Knowledge: https://help.moveworks.com/docs/ingested-knowledge-new#permission-checker Ingested Files: https://help.moveworks.com/docs/ingested-files-new#permission-checkerWe encourage you to explore the Permission Checker tool and share your feedback on the community forum so we can continue to improve it!Thank you,Moveworks Setup Team

The new Agent Architect Panel provides contextual assistances, examples, and best practices to significantly accelerate your workflow, all directly inside Agent Studio.Features + Current Display:The panel contains all functionality of the Agent Architect, but directly within Agent Studio to allow for a direct copilot-like building experience.Panel resizing can be completed as follows:The panel can be collapsed and re-opened for user convenience to allow the desired screen real estate at a per-customer basis to be utilized:

Get the latest on the product releases and roadmap updates to stay up to speed on all the exciting new features our teams are working on! Roadmap plans and any forward looking statements are shared under NDA and subject to change without notice.We also encourage you to check out the monthly release notes for details on past product updates. Enterprise Search10 Next-Gen or Enterprise Search connectors available for setupThese are the newest connectors available for 10 content systems. They support a scale of millions of documents, out-of-the-box permissions support and improved freshness SLAs. These connectors are currently available as part of an upgrade. Please reach out to your account team to learn more about getting access and connecting Moveworks to millions of documents.See our supposed content connectors and their availability status here.Read more about Content Connectors here.New and improved search plugin coming to US and EU in February / MarchWe are rolling out a new Enterprise Search plugin in AI Assistant for all US and EU customers, which uses an upgraded and scale-ready search and relevance ML system. This new plugin represents our new and improved search that is capable of finding the most relevant content across millions of documents.When will the Enterprise Search plugin be available? US customers Thursday, January 22: Early access for customers to try the Enterprise Search plugin Tuesday, February 24: All US customers will be automatically switched to the enterprise search plugin EU customers Thursday, February 5: Early access available for customers to try the Enterprise Search plugin Tuesday, March 3: All EU customers will be automatically switched to the enterprise search plugin Read more about our improved search plugin here.Nominate your organization for early access here. AI AssistantA New Look for Moveworks Web Experiences (Assistant on Web, Enterprise Search, Embedded Assistant)Next Monday, both Assistant on Web (AI Assistant + Enterprise Search) and the Embedded AI Assistant will be updated to reflect Moveworks’ new visual identity. This update brings a cleaner, more modern interface and improves accessibility and consistency across all web experiences.For more details on what will change, see our documentation page here. Moveworks SetupIntroducing Permissions Checker in Ingested Knowledge & FilesThe Permission Checker tool allows Moveworks admins to verify whether a specific user has access to specific knowledge base articles or files by selecting or providing a user’s email address. Read more about when to use the tool as well as access guidelines here.  Nominate your organization for our Limited Preview ProgramsConsult our list of available Limited Previews here.  🚨Important NoteFeature timelines are subject to change due to various underlying factors. Please check in regularly for timely updates.Thank you for being part of our community! If you have any questions or feedback, please feel free to reach out here.