Run Skills in AI for Work
Autonomous agents now support skills. When you add an agent, upload a skill as a folder or .zip file to extend what the agent can do. End users work with the agent directly and don't need to build or manage skills themselves. [Learn more→](/ai-for-work/custom-agents#step-2-configure-agentic-app)Agents as MCP Tools
Administrators can now publish AI for Work agents as tools on MCP servers, making them available to MCP-compatible clients such as Claude and ChatGPT. A guided wizard configures the server, its tools, OAuth authentication, and access limits. [Learn more→](/ai-for-work/assistant-configurations#tools)Manage multiple versions of your agents
Agents now support version history. Publish a version with a custom name and description, and the platform autosaves your ongoing changes as a single draft. Preview any version in read-only mode, restore an older version as a new draft, and manage up to 50 versions per agent. [Learn more→](/ai-for-work/custom-agents/agent-management#version-control)Sync employee data with Google Service Accounts
The Enterprise Directory now supports Google service accounts as a data source, alongside Microsoft, LDAP, and the Push API method. Connect a configured Google service account to sync employee data from your identity provider. [Learn more→](/ai-for-work/administration/user-management#directory-configuration)Model Selection for Memory and Personalization
Administrators can now choose which LLM connection powers memory and personalization. The selector becomes available on enabling at least one memory feature and lists the account's configured LLM connections. [Learn more→](/ai-for-work/assistant-configurations#model-selection)Announcements to User Groups
Administrators can now target announcements to selected user groups instead of the entire account. Choose the user groups option, select one or more groups, and the announcement reaches every member of those groups. [Learn more→](/ai-for-work/assistant-configurations#create-an-announcement)Organization Chart Enhancements
The organization chart now surfaces employees without a reporting manager. Select the unassigned employees option to list them, and expand any employee to view direct reports inline. Administrators can also set the chart root user and override that selection at any time. [Learn more→](/ai-for-work/getting-started/how-to-use#organization-chart)New Model Support
AI for Work now supports `Sonnet 5`, `Opus 4.8`, and `Fable 5`, expanding the model options available for your assistant and agents. [Learn more→](/ai-for-work/llm-configuration#model-tiers)Model Parameters for LLM Connections
Each LLM connection now includes a parameter configuration section, so you can tune model behavior per connection. Adjust parameters such as temperature, max tokens, and reasoning effort, with controls suited to each parameter and a reset to recommended defaults. [Learn more→](/ai-for-work/llm-configuration#model-parameters)Reasoning Thoughts and Tool Visibility
When a reasoning model processes your request, the assistant now displays each tool call as a live label while it works. Click any label to open a side panel showing the complete execution flow, including code inputs and outputs and web search results.Generate images in assistant responses
The assistant can now generate images directly in responses, so you can move from idea to visual without leaving the conversation. *** ## v1.18.0 June 11, 2026 This update includes new features and feature enhancements summarized below.Enterprise Search
A dedicated **Search** experience is now available alongside **Chat**, with its own tab in the left panel. Search results pull from all connected connectors, with connector-specific tabs and filters for **People** and **Timeline**. **Related Searches** appear after the first four results, triggering new searches in the same thread without creating a new one. Administrators can enable **Enterprise Search** under **Assistant Configurations** and select one enterprise knowledge source for search results. [Learn more→](/ai-for-work/assistant-configurations)User Management — Partners
A new **Partners** tab in **User Management** lets administrators view, invite, and manage partner users. All partners invited to the account appear under this tab. Administrators can view partner details, change roles, suspend, delete, permanently delete, and export partner users. Partner invitations are restricted to configured partner domains. If an email address does not belong to a partner domain, an inline error displays: "Invalid domain." If no partner domains exist in **Domain Management**, the Partners page shows an empty state prompting the administrator to add partner domains first, with a link to **Domain Management**. [Learn more→](/ai-for-work/administration/user-management)Additional Language Support
German, Japanese, Spanish, and French are now available as supported languages. Users can select a preferred language from the language settings, and the selected language applies immediately across the application. All system text, including menus, buttons, labels, messages, and notifications, reflects the selected language. [Learn more→](/ai-for-work/assistant-configurations#language-settings)New LLM Models
The **General Purpose LLM** configuration now supports three additional models: `gemini-flash-3.5`, `gemini-flash-lite-3.1`, and `openai-5.5`. Administrators can add these models from the LLM configuration page and use them across agents and platform tools. [Learn more→](/ai-for-work/llm-configuration)Theme Settings — Dark and Light Themes
Users can now select a theme from the profile settings popup in the end-user application. Available options are **System Default**, **Dark**, and **Light**. The selected theme applies immediately across the application UI, persists across sessions, and synchronizes bidirectionally between the end-user application and the **Admin Console**. *** ## v1.17.0 May 18, 2026 This update includes new features and feature enhancements summarized below.LLM Configuration — Anthropic Claude Models
Anthropic is now available as an LLM provider in the **General Purpose LLM** configuration. Administrators can connect using an Anthropic API key and select from Claude Opus, Sonnet, and Haiku model families. Supported models include `claude-opus-4-7`, `claude-sonnet-4-6`, `claude-haiku-4-5-20251001`, and additional versions across each family. [Learn more→](/ai-for-work/llm-configuration#supported-providers)User Groups — Employee Directory Source
Administrators can now create user groups by selecting members from the **Employee Directory**, in addition to manual selection, AD Sync, and file upload. Apply filters based on employee directory fields using AND logic to dynamically define group membership, with a real-time preview of the filtered list before saving. [Learn more→](/ai-for-work/administration/user-management#enterprise-directory)Autonomous Agents — Browse and Link from Agent Platform
Autonomous agent configuration now supports browsing and linking apps directly from the new Agent Platform. Choose **Link App (V1)** or **Link App (V2)** to browse accessible apps across workspaces, or use **Link App with URL** to connect through an endpoint URL and connection secret. Execution mode supports **Sync** and **Async**, with **Async** providing a redirect URL, access token, and connection verification. The same linking experience applies when adding an agentic app to **Enterprise Knowledge**. [Learn more→](/ai-for-work/custom-agents#create-an-autonomous-agent)Prebuilt Tools — AI Models
A new **Prebuilt Tools** page under **Assistant Configurations** provides a centralized view of platform tool, **AI Model**. Administrators can add AI models from configured LLM connections, assign a user-facing name and description, and define publishing scope to **Everyone**, **Selected Users**, or **Selected User Groups**. [Learn more→](/ai-for-work/assistant-configurations#prebuilt-tools)Prompt Agent — Code Interpreter
Prompt Agent configuration now includes a **Code Interpreter** option that allows agents to execute code as part of their response workflow. This option activates for models that support code interpretation. [Learn more→](/ai-for-work/custom-agents#step-2-source-configuration)Service Accounts — Okta Integration
Okta is now available as a service account type in the **Admin Hub**. Administrators can connect their Okta domain by providing an account name, domain URL, and **Admin API Token** for user and group management workflows. [Learn more→](/ai-for-work/administration/security-and-control#okta-2)Slack Channel Enhancements
This release introduces three improvements to the Slack integration. Follow-up queries from the same user now receive contextual responses in threads where **Private Replies** are active, with all follow-ups mapped to the same conversation thread. **Private Replies** now support **Autonomous Agents** and **Search Agents**. Administrators can also select any published agent they have access to in **Publish Settings** and **Channel Customisation**. [Learn more→](/ai-for-work/channels#slack)Personalisation and Memory (Early Access)
The AI assistant now remembers context from conversations and references chat history to deliver personalized responses. Administrators can enable or disable **Referencing Past Chats**, **Capturing Memory**, and **Mining User Data from Business Systems** from a new **Personalisation & Memory** section in the **Admin Console**. Agent creators can define memory instructions during agent setup to control what context each agent retains. A new **Personalisation & Memory** widget on the user profile page lets users manage their persona, configure custom instructions, and review or delete stored memories across agents. [Learn more→](/ai-for-work/getting-started/how-to-use#personalisation-and-memory) *** ## v1.16.0 April 24, 2026 This update includes new features and feature enhancements summarized below.Projects
Create self-contained workspaces where you upload files, define custom instructions, and carry context across conversations, so you can ask queries without re-uploading documents or repeating background information every time. Each project maintains its own knowledge base, conversation history, and compose bar scoped to the project's content. * Create a project with a name, optional instructions, and file uploads (PDF, DOCX, PPT, TXT up to 25 files, 15 MB each). Instructions guide how responses are generated whenever you query within the project. * The project detail view displays files, instructions, and recent threads in the left panel, with a project-scoped compose bar, auto-generated smart suggestions, and custom sample queries in the right panel. * Hover over any file to **Ask** about it individually, or select multiple files for bulk actions (delete, move, query). * Project threads appear in History with a project icon and reopen with full project context preserved. * Share projects with specific users as read-only. Users with whom project is shared can view files, suggestions, and sample queries, but cannot modify project settings. [Learn more→](/ai-for-work/getting-started/how-to-use#projects)Document Generation
Generate documents directly in the chat interface without downloading. This feature is available only when using the OpenAI model. Supported formats include PPT/PPTX, DOC/DOCX, XLS/XLSX, and PDF. Mermaid diagrams and HTML code render visually with a toggle to switch between the rendered view and raw source.Left Panel Navigation Updates
The left navigation panel now includes an **Account Switcher** at the top, allowing users to switch between accounts they have access to. The Switcher is available when more than one account is available. The **History** section displays the four most recent threads inline. A **See All** option opens a pop-up with all threads grouped by date (Today, Yesterday, and specific dates) *** ## v1.15.0 March 30, 2026 This update includes new features and feature enhancements summarized below.Employee Organization Chart
The Employee Directory now includes an **Organization Chart** tab that displays the organizational hierarchy visually. Expand employee cards to view direct and indirect reports, apply filters, and search for specific employees. The chart automatically focuses and expands to the matched user. Open the full profile view from any card. Zoom, fit preview, collapse, and full-screen controls are also available. [Learn more→](/ai-for-work/getting-started/how-to-use#organization-chart)Feedback Management and Email Notifications
Introducing a dedicated **Feedback** page under **Usage** in the Admin Console. Administrators can now view, filter, and drill into user feedback across all agents and workspaces, with access scoped by role. Account-level admins see all feedback across the account, Workspace Owners see feedback within their workspace, and agent-level access scopes feedback to that specific agent. End users can now choose from an expanded set of feedback categories when submitting upvote or downvote feedback, including Forgot previous context, Outdated, Wrong formatting, and Other, in addition to the existing options. [Learn more→](/ai-for-work/analytics#feedback-management)UI Localization and Language Support
AI for Work now supports multi-language localization. On first login, users can select their preferred language from the language selection module. All static and dynamic UI text updates immediately across the application. Users can change their language preference at any time through the profile icon. Arabic includes full RTL layout support. All UI elements, including the history panel, response area, menus, and icons, realign to RTL automatically. [Learn more→](/ai-for-work/assistant-configurations#language-settings)Drag-and-Drop File Upload
Users can now drag and drop files directly into the AI for Work chat interface, in addition to the existing attachment icon workflow. The drop zone highlights on hover, and the upload initiates automatically once a file is dropped. [Learn more→](/ai-for-work/getting-started/how-to-use#uploading-files)Scoped Source Selection for Search Agents
When configuring a Search Agent or adding a Search App to Enterprise Knowledge, users can now select or deselect specific sources, including websites, file uploads, and connectors, from the linked Search AI app after authentication. Previously, all available sources connected by default. Previously selected sources are retained when editing credentials or sources. [Learn more→](/ai-for-work/custom-agents#step-2-configure-search-index)Search Filters
Users can now filter search results in the search results panel by Timeline, Created By, and File Type. The Timeline filter supports predefined ranges and a custom date picker. Created By supports multi-user selection with a searchable pop-up, and File Type options populate dynamically based on the current result set. *** ## v1.14.0 March 2, 2026 This update includes new features and feature enhancements summarized below.Attachment Settings
Introducing **Attachment Settings** under **Assistant Configurations** in the Admin Console, giving administrators centralized control over file attachment behavior in the compose bar. Key capabilities include: * Enable or disable attachments for end users in the compose bar. Attachment uploads require at least one configured LLM model. * Select the LLM model used to process uploaded attachments. Model changes take effect immediately. * Allow attachments larger than the model context size by enabling RAG-based processing. Choose between **Model-based RAG**, which uses your configured LLM model to handle retrieval and generation, or **In-house RAG**, which uses the platform's built-in retrieval pipeline without relying on an external model. [Learn more→](/ai-for-work/assistant-configurations#attachment-settings)Employee Lookup Settings
Introducing **Lookup Settings** under the **Employees** section in the Admin Console, giving administrators control over how the AI assistant answers employee-related queries. Enable or disable Employee Lookup and select a lookup source: Employee Directory, Service Account, or From User Data. [Learn more→](/ai-for-work/administration/user-management#lookup-settings)Centralized Schedulers Tab
The platform introduces a new **Schedulers** tab under **Agents and Flows**, providing a unified interface for creating and managing all automated schedules. Create schedulers for any agent, flow, or mode (Work, Web, AI Model) you have access to, directly from a single location. [Learn more→](/ai-for-work/custom-agents/agent-management#schedulers)Enterprise Directory — Service Account Source
The Enterprise Directory now supports **Service Accounts (Microsoft, LDAP)** as a data source, in addition to the existing Push API method. Connect a pre-configured service account to automatically sync employee data from your identity provider, map fields between the source system and the directory, and configure manual or scheduled sync with Daily, Weekly, or Monthly frequency options. [Learn more→](/ai-for-work/administration/user-management#enterprise-directory)