We are excited to share that the Conversations API is soon launching into the Controlled Availability phase!For the first time, you can put the Moveworks Assistant behind your own surfaces, your own desktop and mobile apps, internal portals, orchestration layers, and test harnesses, over a simple REST interface, without having to own a native chat experience.Why we built itMoveworks has always powered the surfaces employees already use (Slack, Teams, embedded web chat, etc.). The Conversations API extends that reach: it is the programmatic interface to the Assistant, bringing knowledge lookup, plugin execution, multi-turn conversations, and proactive messaging to any surface you build. It is the same Assistant your employees know, now available wherever you need it.What you can do in Controlled AvailabilityMulti-turn conversations with server-managed context, so you never resend prior turns. Slot filling and disambiguation are handled for you. Assistant-driven search with citations grounded in your ingested knowledge. Agentic workflows: run Agent Studio plugins and native actions (ticketing, PTO, access provisioning) through conversational flow. Proactive delivery: approvals, ambient agent messages, and Employee Comms campaigns delivered as events. Richer button interactions: slot disambiguation, confirmation groups, single and multi static selects, URL and redirect buttons, and native plugin follow-up buttons. Feedback submission (helpful / unhelpful plus free text) attributed back to Insights. Standardized authorization: Authorization Code flow for core IDPs (Okta, Azure, etc.) and self-signed JWT for service and agent requests with user impersonation.The surface is built on four constructs, Conversations, Responses, Messages, and Events, supporting synchronous, asynchronous, and proactive interaction patterns.Who it is forControlled Availability is a great fit if you are looking to:Bring Moveworks to custom desktop, mobile, or portal surfaces beyond Slack and Teams, including branded front doors for your full employee base. Embed Moveworks inside an internal router or orchestration layer that decides which AI handles a query. Programmatically evaluate Assistant responses on a cadence.You can deploy your integration to a pilot cohort of end users to test your integration, and further to your broader organization!SKU Eligibility & Pricing Packaging Inclusion: The Conversations API will be included for customers on EmployeeWorks and Moveworks Standalone packages. (Note: It will not be included in AI Native SKUs). Eligibility: Customers must hold an active EmployeeWorks or Moveworks Standalone contract to participate in Controlled Availability. A Note on Controlled AvailabilityControlled Availability is intentionally less opinionated about UX at the API layer than our native Slack and Teams experiences. A few capabilities (in-modal form rendering, handoff fallback for legacy deflections, and per-integration analytics tagging) are not yet supported, and your feedback during this phase will directly shape what ships at GA.How to sign upSign-ups are open now. Access is curated by our Product team, and accepted nominees will begin onboarding on July 20. To request access, fill out the sign-up form here. We will review your submission and reach out to discuss fit and next steps.What to expect before you sign up: This is API access, not a turnkey feature. To get the most out of Controlled Availability, you should come in with a pilot integration in mind that you want to build, and have technical resources or developers available to build it on top of the API.We cannot wait to see what you build! Questions or ideas? Drop them in the comments below. 

Installing a plugin used to be messier than it needed to be.If the target org already had a connector, HTTP action, compound action, or conversational action with the same name, Agent Studio created forced you to create another copy by renaming it. One install could leave you with Create Ticket, Create Ticket (1), Create Ticket (2), then a bunch of manual cleanup to figure out which one was the real thing.That changes today. Reuse Existing Assets on Plugin Install is now GA for all customers.When you install a plugin from Marketplace or import one from another environment, Agent Studio now checks for matching assets by name in the target org. For each match, you can choose:Incoming asset ChoiceServiceNow connector Use existing or configure newCreate ticket action Use existing or configure newNotify user action Use existing or configure newPick Use existing and the plugin points at the asset already in that org. Anything new still gets created as new.What this fixes:→ Less asset sprawl after installs→ Less manual rewiring after sandbox-to-prod promotion→ Same install flow for Marketplace installs and environment importsThe important caveat: this is reuse, not overwrite. Agent Studio does not modify the asset you reuse, and this does not add version history or rollback. If you need a separate copy, choose Configure new.You'll only see existing assets you're allowed to reuse.If plugin installs have left your org with a trail of duplicate actions, try the new flow and tell me where it still feels rough.

🚀 Big newsWe just made getting answers in EmployeeWorks even faster and easier to share. No more telling colleagues, "Go to EW and type exactly this."Starting today, EmployeeWorks now officially supports Prefill Deep Links!What’s New?You can now construct a custom hyperlink that opens EmployeeWorks with a query already provided to the Moveworks Assistant. When a teammate clicks it, they land right in their own EW portal with the query already being worked on by the Assistant.Here is the URL format to build your own:https://{your-instance}.service-now.com/aiux/employeeworks/chat?mw_route=%2Fassistant%3Fmessage%3D{your-query}Where {your-query} is your question, URL-encoded (spaces become %20, question marks become %3F).💡 See It In ActionCheck out how these look in practice: How do I create an email signature? 👉 https://{your-instance}.service-now.com/aiux/employeeworks/chat?mw_route=%2Fassistant%3Fmessage%3DHow%20do%20I%20create%20an%20email%20signature%3F When clicked, will redirect the user into Moveworks with the provided query. I got locked out of my laptop what do I do? 👉 https://{your-instance}.service-now.com/aiux/employeeworks/chat?mw_route=%2Fassistant%3Fmessage%3DI%20got%20locked%20out%20of%20my%20laptop%20what%20do%20I%20do%3F The response will return just like if they queried Moveworks directly. ✨ Bonus Feature: Want to deep-link to an Enterprise Search result instead of the assistant? Use the same pattern but swap the route to mw_route=%2Fsearch%3Fquery=...How to Use It To Supercharge Your Workflow "Try This in EW" Buttons: Embed prefilled links into your internal documentation, wikis, runbooks, or onboarding labs so users can test queries instantly. Share Perfect Prompts: Crafted the perfect question that yields the exact answer you need? Send it to a teammate so they can run it on their own account. Intranet & Banner Shortcuts: Link directly from your intranet tiles or Self-Service Portal (SSP) banners straight to a specific EW use case rather than tgeneric homepage. ⚡ Live Right NowPrefill deep links are officially live and deployed across all EmployeeWorks instances. Start building your links and streamlining your team's workflows today!

We're retiring the legacy Control Center (the old admin interface) on July 10, 2026.All administration and configuration for your Moveworks environment is now available in My Moveworks at my.moveworks.com, which leverages your company's SSO for access. My Moveworks is a full replacement for the legacy Control Center — there is no loss of functionality, and no migration work is required on your side.If you've been accessing the older admin experience, you've already been automatically redirected to the new experience over the past two months. After July 10, the legacy URL will no longer be available.What you need to do: Nothing in most cases. If your organization experiences any issues during this transition, please open a Moveworks Support case and our team will help! Old Experience Page being sunset. Currently, users are being redirected to the new experience.New ExperienceNew experience users have been automatically redirected to for the past 2 months.  

 We've made it faster to get to the exact interaction you're troubleshooting. Chat Playback now lets you look up history by Trace ID, in addition to Conversation ID.Why it helpsPreviously, you needed the full Conversation ID to replay an interaction. Now, if you're already in your logs investigating an issue, you can grab the ID right there and jump straight into Chat Playback — no extra steps to track down the conversation.How it works1. In Chat Playback, use the dropdown to pick your lookup type:  - Conversation ID — loads the entire conversation, so you can step through every turn.  - Trace ID — takes you straight to the single interaction turn.2. Copy the ID from either the logs view:  - Built-in Plugin Logs → the Trace ID column  - Agent Studio Logs → the UUID column3. Paste it into Chat Playback and press Enter.That's it — you'll land right on the conversation or the specific turn you're after.📖 Full details in the docs: AI Assistant Chat Playback: Link  

 We've shipped two improvements to Moveworks Setup that make configuring your assistant smoother and troubleshooting conversations dramatically faster.---1. A simpler, smarter Ticketing Configuration wizardSetting up a ticketing integration just got cleaner. The Ticketing Configuration wizard now uses a single, context-aware action button in place of the separate Save and Next buttons.Instead of deciding which button to press on each step, the wizard shows you the right one automatically:- Next when there's nothing to save- Save and Next once you've made changesThe result is one clear path forward through every step of setup — less clicking, less second-guessing, and fewer accidental "did I save that?" moments.This is available org-wide with no extra configuration required.📄 Learn more: Ticketing Configuration ---2. Chat Playback transcripts now land in ~10 minutesChat Playback lets you replay any user conversation with the AI Assistant to debug issues and troubleshoot with your partners. The biggest friction was the wait — transcripts used to take 3–4 hours to become available.Now, transcripts surface within ~10 minutes of a conversation completing.That means when a user reports an issue, you can pull up the session and see exactly what happened almost right away — including:- The full conversation replay: the user's question, the assistant's reasoning, its responses (text and cards), and citations- The detail behind each turn: plugin steps, plugin selection and execution, intent, and how the final response was generated 📄 Learn more: AI Assistant Chat Playback 

To improve the user experience, we're updating how bold text works across responses on the web. Bold now serves as a structural tool only, appearing in two places: standalone headings when heading syntax isn't available, and short run-in labels at the start of a paragraph, followed by a colon. Key DatesFrontier: June 29, 2026Standard: July 1, 2026Basic: July 6, 2026BeforeAfter  Learn more about our model upgrades here.

For customers in Controlled Availability, Agent Studio now supports folder-based access control and role-based permissions, so you can open up development to more teams without exposing sensitive connectors or putting live plugins at risk.What was the problem?Every developer in your Agent Studio tenant could see, edit, and publish every asset, including connectors to sensitive systems like Workday or ServiceNow. The only safe option was keeping Agent Studio locked to a small set of trusted engineers, which directly limited how fast teams could scale.What's includedFolders: Public (org-wide), Personal (drafts), and admin-created custom folders (e.g., "HR Integrations"). Assets inherit folder permissions automatically. Four roles: Manager, Developer, Operator, Viewer, assignable per user per folder or asset. Dependency enforcement: Running an asset requires Use permission on its full chain, including every action and connector it calls.  Boundary states: When blocked, the UI names exactly what's missing and surfaces a "Contact owner" prompt.How to get accessThis feature is in Controlled Availability for a curated set of design partners. Key limitations in this release: no group-based permissions (individual users only), flat folder structure only, no bulk admin actions, and MCP Servers are outside RBAC scope.Docs: linked here   

 🎉 Slack UX Improvements Now in Controlled Availability!We’re excited to announce that our new Slack UX Improvements package is now available in Controlled Availability.These updates introduce a set of interface enhancements designed to deliver a best-in-class Slack experience, improve trust in responses, and enable users to complete more work directly within Slack channels and DMs.In making agent interactions more transparent, your team can now interact with Moveworks in a far more intuitive, responsive, and visually rich environment.What is included in the Slack UX ImprovementsLaunch Native Global Actions, allowing Slack native popups directly within the chat interface to speed up task ​​​​Already included in the Slack UX RolloutOnce accepted into the Controlled Availability, your organization can validate Global Actions.These features will be deployed and validated with a small cohort of customers ahead of general availability. If your organization has already deployed Channel Resolver, you are an ideal candidate for this early phase.📝 Join the CA (if not already enrolled):Self-Nominate for Slack UX Improvements Controlled AvailabilityIf you have questions, ideas, or would like to showcase what you’re building, share them below - we’d love to hear from you!​ 

We are thrilled to announce that Enterprise Search Insights is now available to all customers who have Enterprise Search enabled for them.This dashboard fundamentally answers three questions : Who is using Enterprise search ?  How is Enterprise search being used, what are users doing on it ?  How to improve it ?   

We're excited to share that we are beginning to support GPT-5.4 in the Moveworks Reasoning Engine. We put GPT-5.4 through extensive internal testing before bringing it to you.Stronger Instruction Following. GPT-5.4 adheres more closely to the instructions that shape your plugin's behavior, resulting in more consistent, predictable outputs aligned to your configuration.Improved Cited Answers. When your assistant responds with information from your knowledge base, it now includes links back to the source documents far more consistently. Users get answers they can verify, not just bare claims.Improved Tool-Call Argument Filling. When your assistant calls a tool, it more accurately extracts the right information from the conversation. Whether it's a ticket title, a PTO date, or an employee ID, GPT-5.4 more reliably finds the particular values it needs.Why we’re so methodical with the upgradesBefore rolling out any new model, our team runs it against a suite of internal benchmarks. We then stage the rollout across tiers (Frontier first, followed by Standard and Basic) so that any issues surface in a controlled way before reaching your environment. It's how we make sure upgrades feel like improvements.When will GPT-5.4 be available in Moveworks?Target release dates by tier below:Frontier: Wednesday June 10, 2026Standard: Wednesday July 8, 2026Basic: Wednesday September 9, 2026Note: Dates are for all accounts including GovCloud accounts. 🚧 Is there anything I need to do for this rollout? This change will be made to your plugin automatically during this period. There is no additional setup work required, nor any expected downtime.🛑 Are there any known issues? GPT-5.4's improved instruction adherence means that misconfigured or misaligned instructions in your plugin could have a more pronounced effect on behavior. If you see misaligned behavior, check the tool description, slot description, and the display instructions configurations within the plugin to more finely tune the desired response. 

You can now reference custom domains directly in Ticket Routing and the Workflow DSL. Multiple custom domains can coexist in a single tenant, each routed to its own ticketing workflow.What was the problem? Ticket routing worked by domain type (IT, HR, Facilities…), but couldn't distinguish between specific custom domains within a type. If you had more than one custom domain, your routing rules couldn't tell them apart. The only workaround was spinning up a separate ticketing integration per custom domain.What's newA new field, domain_destination, is now available in Ticket Routing. Add a custom domain in the panel, then reference it in your Workflow Routing and Workflow DSL.How to configureSetup → Ticketing Configurations → Routing & Workflow Conditions → Conditional Routes → DSL Routing RulesRoute on a specific custom domain or default domain:context.system_context.domain_destination IN ["<domain_name>"]NoteThe new field domain_destination covers both default and custom domains. Please start using this field going forward for either default or custom domains.For default domains, the value is the domain name without any suffix:IT_DOMAIN → "IT" FACILITY_DOMAIN → "FACILITY" HR_DOMAIN → "HR"

We've released the Tool Response Rendering Improvements ML upgrade for Standard customers.Tool Response Rendering ImprovementsWe've made some updates to how the Moveworks AI Assistant presents tool responses!The Assistant now presents clean and concise results. Previously, some responses were excessively verbose or surfaced extra, unnecessary information, rather than synthesizing it into a helpful answer. Improvements include four changes that will make responses clearer:Relevance by default: When sharing information from a tool response, the Assistant surfaces only details relevant to your request. Raw data fields, internal identifiers, and technical values you can't act on are omitted. Synthesized answers: When multiple tools contribute to a response, results are combined into a single coherent answer. Plain-language errors: When a tool encounters an error, the Assistant describes the outcome in plain language. Clean output by default: The Assistant won't include verbose technical data in responses unless it's directly useful to you.To verify the improvementsAfter the update is live in your environment: Ask a question that normally triggers a verbose tool response. The Assistant should return a concise, relevant answer.Read more about the release here.Learn more about our model upgrade program here.

 6/4 update: Vetted Content is now live on Assistant (Web, Slack and Teams) in addition to the Enterprise Search Web App! Thank you for your patience as we worked through the remaining items — we're excited for you to try it out. We’re launching a new feature called Vetted Content which will be generally available (GA) on May 28, 2026 on Enterprise Search Web App to help employees instantly recognize approved, authoritative answers in Moveworks Assistant and Enterprise Search. Please note: this update is designed to work best with GPT-5.2, currently in our Frontier and Standard plans (link). Under GPT-5.1, Vetted Answers may not perform optimally.What it isVetted Content clearly signals which indexed files and Knowledge Base Articles (KBAs) are approved by your organization, so employees can quickly trust the answers they see. Use Vetted Content to improve trust when your organization contains outdated or unmaintained content, multiple documents cover similar topics and employees can't tell which is authoritative, or when content has been created by individuals/teams outside the designated subject matter owners.In Moveworks Assistant, responses cited from vetted sources appear in a prioritized "From vetted sources" section at the top of the answer. Available across Web, Slack and Teams.In Enterprise Search Web App, vetted results carry a Vetted badge, and the Search summary is split into two parts: vetted sources first, then other top sources. Vetted results also receive a small ranking boost when relevant (search results ordering remains primarily relevance-driven; vetting isn't a hard pin).Admins can vet any indexed files or KBAs in Moveworks Setup completely self-service, no engineering or support ticket required.    Benefit to employeesTrust at a glance. Employees can see which answers come from approved, authoritative content without guessing. Less doubt, faster action. Reduce "is this still correct?" hesitation around policies, runbooks, and how-to guides. Easier discovery. The right answer is more likely to surface in Enterprise Search App when it's truly the source of truth.Next stepsWant a sneak peek before GA? Reach out to your Customer Success Manager to preview Vetted Content in your sandbox before the May 28 launch. Plan for launch. Once GA goes live, admins can start marking files and knowledge base articles as vetted in Moveworks Setup through self-service. We will update this post with a setup guide.

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.AI AssistantWorld Knowledge App - Available Now (for customers on EmployeeWorks and Standalone SKUs)Users can search and synthesize information from public web sources, upload files, and get help with editing and writing.Channel Resolver - Controlled Availability in June 2026Users experience the Assistant responding to channel messages and live agent hand-offs in their Direct Messages.Slack Chat Threads - Controlled Availability in June 2026Introduces chat threading for a clean, modernized experienceSlack Native Popup & Global Actions - Controlled Availability in May 19Users will now see references pages popup within SlackAgentic Reasoning EngineTool Response Rendering Improvements (dates below)CA: May 15 - 18Standard: May 18 - May 20Basic: May 20 - May 25Users will see streamlined output from the AssistantNote: Because this feature impacts the underlying ML we will be rolling it out using the tiers described in the Model Upgrade Program. You can read more about that program here. Enterprise SearchEnterprise Search Plugin Migration + MLS - Available NowCustomers unlock scale with max capacity connectors and experience, improved relevance quality and more reliable results for all non-English speaking usersMLS for Files - Available NowUsers can now ingest non-English filesVetted Answers - Available NowUsers now see answers that have been vetted by the organization, as accurate and high quality, at the top when asking the Assistant a question.Search Analytics - Coming June 20, 2026Users will be able to track search metrics, user trends, and trending topics to better understand the quality of informationSelf Service/SetupIdentity 2.0 - Available NowUsers can now ingest users from external systems in minutes instead of hoursManual User Management - Available NowPartner Development Instance users can now test plugins and connectors without SSO or identity ingestion dependencyPartner Development Instance Offboarding - Coming in June 2026PDI users can now automate the org lifecycle management to scale partner enablementSelf-Serve Validation Failure Alerts - Coming in June 2026Partners can now independently diagnose and resolve ingestion blocking scenarios for Users & Forms.Note: KB, Access Groups, and FAQ Resources are currently out of scope.

🎉 Now Available: EmployeeWorks We're excited to share that EmployeeWorks is now generally available! What is EmployeeWorks?EmployeeWorks is an AI-native web experience — dynamic, context-aware home for your entire workforce — a single interface that surfaces the tasks, requests, and information most relevant to each employee, generated and personalized by AI. With this release, Moveworks plugs directly into that interface, so the conversational AI Assistant your employees already know is right there, embedded within Employee Slate. What this unlocks for your employees:One front door for work. Employees land on a view tailored to their role, team, and recent activity — with Moveworks ready to act on any request. Conversational depth, visual context. Quick searches, ticket resolutions, and approvals stay conversational with Moveworks; longer workflows and structured tasks render natively in Employee Slate. Cross-system reach you already have. Every connector, plugin, and skill in your Moveworks deployment is available — no rebuilding needed. Personalization that improves with use. Employee Slate learns from how employees interact with it and keeps their home pages maximally  relevant. World Knowledge Assistant. Gives employees a secure, GPT-like space for content generation, web searches, troubleshooting help, and more. Read more about it here  Who it’s for:Available for customers who have purchased EmployeeWorks. Contact your account team for a demo or more information. Learn more here. Read how to get started here. Questions? Drop them in this thread — our team and the broader community will jump in. And if you're already piloting Employee Slate, we'd love to hear what's working (and what isn't).

We've released the Improve User Message Context during Entity Selection model upgrade to Standard customers.Improvements to how the AI assistant identifies and selects the right applications and resources when processing user requests. This update ensures that customer-configured catalog items are prioritized over generic defaults, leading to more accurate plugin responses — particularly for software access workflows.Read more about the release here.Learn more about our model upgrade program here.

What problem does this solve?Knowledge workers need help every day with tasks that have nothing to do with company data — rewriting an email, debugging a SQL query, finding the latest security patches, or checking whether a benefits document still complies with current law. They need a secure, capable thought partner. Many organizations restrict consumer AI tools on corporate devices for security and compliance reasons, and standalone AI subscriptions add cost without integrating into existing workflows. Employees end up without a reliable, sanctioned option for everyday knowledge work.World Knowledge App gives employees a secure, enterprise-grade AI assistant for general-knowledge work — accessible inside the interfaces they already use. Step-by-step: how does it work? Employee opens the World Knowledge App. It appears as a dedicated app in the left panel of Web (either Moveworks Web or EmployeeWorks Web). It is separate from the Universal Assistant so general-knowledge conversations stay focused.Employee asks a question. The assistant handles the full range of general-knowledge tasks: improving writing, learning a concept, finding current information, debugging code, or analyzing a document.The assistant decides whether to search the web. When LLM knowledge alone isn't sufficient — for example, "Were there recent security patches for Adobe products?" — the assistant automatically triggers a live internet search. No user confirmation needed. Every web-sourced response includes citations so employees can verify the source.Optionally, the employee uploads a file. They can attach a document and ask questions that blend the file's content with LLM knowledge and live web search. Example: "Does this benefits document still comply with current federal law?" The assistant combines what's in the file with what it knows and what it can look up. How to Get Started Availability: EmployeeWorks and Moveworks Standalone SKUs. Not available for AI Native or Heritage SKUs.Enable the app: Moveworks Setup → Core Platform → AI Assistant → Specialized Assistants → activate World Knowledge App Enable file attachments: Moveworks Setup → Manage Chatbots → select the Web bot → enable File Attachment Manage web search (optional): Moveworks Setup → Plugin Management → World Knowledge (default: enabled). Recommended to leave on — disabling web search increases risk of hallucinated or outdated answers. Admins with security or compliance constraints can turn it off here.Validation stepsThe World Knowledge App appears as a named app in the left panel on web. A general-knowledge question (e.g., "What are the latest NIST password guidelines?") returns a response with source citations Uploading a document and asking a question returns a response that draws on both the file and external knowledge Disabling web search in Plugin Management removes live search results from responses (LLM-only mode)

We've released the Improve User Message Context during Entity Selection model upgrade to Standard customers.Improvements to how the AI assistant identifies and selects the right applications and resources when processing user requests. This update ensures that customer-configured catalog items are prioritized over generic defaults, leading to more accurate plugin responses — particularly for software access workflows.Read more about the release here.Learn more about our model upgrade program here.

We're making a small change to the language we use when rolling out new features — and we wanted to give you a heads up.Going forward, what we've been calling Limited Preview will now be called Controlled Availability. This aligns our terminology with ServiceNow's, making it easier to have consistent conversations across both platforms.What does this mean for you?Same experience, new name. Controlled Availability works the same way Limited Preview always did: early access to features for a select group of customers before broader release. The experience, the process for getting access, and how we communicate with you about it are all unchanged.You'll start seeing "Controlled Availability" in our roadmap updates, release communications, and documentation where "Limited Preview" used to appear.As always, if you're interested in early access to upcoming features or have questions about anything in our roadmap, feel free to reach out or drop a comment below.

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 configureChat Platforms → Display Configurations → Moveworks AI Assistant Display Settings & Disclaimers → Safety Guard: Allowed Content Categories Controls will be made available by EOW (5/9)   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