> For the complete documentation index, see [llms.txt](https://docs.devolutions.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.devolutions.net/powershell-universal/whats-new.md). # What's new? Read what is new in PowerShell Universal 2026.3, including Devolutions Agent integration, container jobs, persistent MCP environments, and an updated admin console. For a complete list of changes, see the [PowerShell Universal release notes](https://devolutions.net/powershell-universal/release-notes/). ## 2026.3 ## Admin console redesign The redesigned admin console offers a cleaner, more consistent experience with refreshed themes, streamlined navigation, updated tables and settings, breadcrumbs, a floating toolbar, and system-wide search. Navigation is grouped into **Build**, **Run**, **Observe**, **Manage**, **Source Control**, and **Secure**, with related pages combined into tabbed hubs. You can pin and customize menu entries, open instance settings from the sidebar gear, and access user settings from the user menu. Available items depend on your permissions, license, and enabled features, and the sidebar adapts to mobile displays. ### AI Agent Chats AI agent chats add a resource-aware conversation to the admin console. Sessions show tool-call and file-change activity, and report input, output, and total token usage so you can understand how an agent handled a request. ### MCP Tool Execution Controls Set a per-minute request limit for MCP tool calls to protect the server from excessive traffic. You can also select the PowerShell environment and computer or computer group where an AI tool runs, giving administrators more control over execution placement. ### Persistent Job and MCP Environments Enable persistent runspaces for an environment to reuse job processes, with separate processes for each environment and credential. MCP tools honor their configured environment, so they can run in the same dedicated execution environment as your jobs. ### Devolutions Agent Integration Devolutions Agent can connect to PowerShell Universal over gRPC to run commands and scripts on remote machines. PowerShell Universal initializes the agent repository and copies scripts for a job, with an option to retain run scripts on the agent. This integration requires Devolutions Agent 2026.3.x or later. ### Container Jobs Run jobs in isolated containers through container execution environments. PowerShell Universal starts a Devolutions Agent container for each job, supports a configured image URL and tag with optional image pulling, records container startup and cleanup output with the job, and removes the container when the job finishes. ### Workflow Branching Use Flow Decision activities to route workflow steps based on true and false outcomes. The workflow designer supports branching alongside PowerShell script and AI prompt activities, making it easier to model conditional automation. ### System-Wide Admin Console Search Search the admin console for applications, cache entries, endpoints, identities, jobs, scripts, and workflows from one place. Search results respect the permissions of the signed-in user. ### Folder-Level Script Permissions Apply permissions directly to script folders from the script folder view. This makes it easier to manage access to related scripts as a group. ### Pester Test Automation Start Pester test runs with `Invoke-PSUTest`. Target a test file or folder, filter by tag or test name, wait for completion when needed, and optionally return parsed test suite results. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.devolutions.net/powershell-universal/whats-new.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.