Cursor ai
ComponentUpdates related to the ai component of Cursor.
All AI Features
- Enabled integration with Jira, allowing users to assign work items to Cursor or mention @Cursor in comments to start a cloud agent session.(05-19-26)
- Cursor now uses Jira work item details (title, description, comments) and repository settings to scope tasks initiated from Jira.(05-19-26)
- Agent completion updates are now shown directly in Jira, including a link to the generated pull request.(05-19-26)
- Introduced Composer 2.5, offering substantial improvements in intelligence and behavior over Composer 2.(composer-2-5)
- Enabled Composer 2.5 to be better at sustained work on long-running tasks.(composer-2-5)
- Enabled Composer 2.5 to follow complex instructions more reliably.(composer-2-5)
- Enabled integration with Microsoft Teams, allowing users to mention @Cursor in any Teams channel to delegate tasks or pull information.(microsoft-teams)
- Introduced automatic repository and model selection based on the prompt and recent agent activity.(microsoft-teams)
- Enabled the agent to read the entire conversation thread for context before implementing a solution and creating a Pull Request.(microsoft-teams)
- Introduced a new, comprehensive PR review experience allowing users to manage PRs from creation to merge within Cursor.(3.3)
- Enabled faster plan execution through parallel agent execution, allowing Cursor to multitask across independent plan steps simultaneously.(3.3)
- Added quick-action pills for pinning frequently used skills for faster access.(3.3)
- Enabled splitting changes into multiple Pull Requests directly from multitasking actions using chat context to identify logical slices.(3.3)
- Made the /multitask command available in the editor for running async subagents to parallelize requests immediately.(3.3)
- Introduced granular model access controls allowing admins to set allow or blocklists at the model and provider level.(05-04-26)
- Enabled blocking of entire providers or specific model configurations based on speed and context window size.(05-04-26)
- Added the option for enterprises to block new providers or model versions by default.(05-04-26)
- Enabled setting of soft spend limits instead of only hard limits to prevent accidental user blocking.(05-04-26)
- Implemented automatic usage alerts sent to users when they reach 50%, 80%, and 100% of their soft or hard limits.(05-04-26)
- Added the ability for admins to filter usage analytics by specific users.(05-04-26)
- Enabled breaking down usage analytics by product surface, including clients, Cloud Agents, automations, Bugbot, and Security Review.(05-04-26)
- Introduced the Cursor SDK, allowing users to build custom agents using the same runtime, harness, and models as Cursor.(sdk-release)
- Enabled running custom agents locally or on Cursor's cloud against a dedicated VM using any frontier model.(sdk-release)
- Added first-class run streaming support via SSE events with reconnect capabilities for Cloud Agents API.(sdk-release)
- Added explicit agent lifecycle controls including archive, unarchive, and permanent delete functionality for durable agents.(sdk-release)
- Introduced the new Agents Window interface allowing users to run many agents in parallel across repos and environments (locally, worktrees, cloud, SSH).(3.0)
- Enabled Design Mode within the Agents Window to annotate and target UI elements directly in the browser for more precise feedback.(3.0)
- Added keyboard shortcuts for Design Mode: → ⌘+Shift+D to toggle, Shift+drag to select an area, → ⌘+L to add element to chat, and → Option+click to add element to input.(3.0)
- Added Agent Tabs in the Editor to view multiple chats side-by-side or in a grid.(3.0)
- Added a new command /worktree that creates a separate git worktree for isolated changes.(3.0)
- Added a new command /best-of-n that runs the same task in parallel across multiple models in isolated worktrees and compares outcomes.(3.0)
- Enabled MCP Apps to support structured content for richer tool outputs.(3.0)
- Added directory group name to audit logs for improved human readability.(3.0)
- Added a team-level Admin setting to restrict creating, editing, and deleting team secrets to Admins.(3.0)
- Added an Enterprise Admin control for disabling "Made with Cursor" code attribution for the entire team.(3.0)
- Introduced Subagents, specialized, independent agents that run in parallel with custom configurations for faster, more focused task execution.(2.4)
- Enabled direct image generation from the agent using text descriptions or reference uploads, saving previews inline and to the assets/ folder.(2.4)
- Launched Cursor Blame (Enterprise plan feature) extending git blame with AI attribution, showing which lines were AI-generated (by Tab completions or agent runs) versus human-written.(2.4)
- Added the ability for agents to ask clarifying questions during Plan and Debug modes, allowing them to continue working while waiting for user input.(2.4)
- Enabled building custom subagents and skills that utilize the new 'ask question tool'.(2.4)
- Added the agent models command to list all available models.(CLI)
- Enabled quick switching between models using the --list-models flag or the /models slash command.(CLI)
- Introduced the /rules command to create new rules and edit existing ones directly from the CLI.(CLI)
- Enabled enabling and disabling MCP servers on the fly using the /mcp enable and /mcp disable commands.(CLI)
- Introduced AI Code Reviews directly in the editor to find and fix bugs within your changes via a sidepanel.(2.1)
- Enabled Instant Grep (Beta) so that all agent-run grep commands, including manual sidebar searches and regex searches, execute instantly across all models.(2.1)
- Introduced a new Multi-Agents editor featuring a sidebar for managing agents and plans.(2.0)
- Enabled running up to eight agents in parallel on a single prompt using isolated environments (git worktrees or remote machines).(2.0)
- Introduced Composer, a new agentic coding model that is 4x faster than similarly intelligent models.(2.0)
- Launched Browser functionality to General Availability (GA) with added support for Enterprise teams.(2.0)
- Enabled Browser to be embedded in-editor, including new tools for element selection and forwarding DOM information to the agent.(2.0)
- Enabled defining custom commands and rules for your Team via the Cursor dashboard, automatically applied to all members.(2.0)
- Introduced Voice Mode, allowing control of the Agent using built-in speech-to-text conversion.(2.0)
- Enabled defining custom submit keywords in settings to trigger the agent to begin running in Voice Mode.(2.0)
- Enabled creating plans with one model and building the plan with another, with options for foreground, background, or parallel agent execution.(2.0)
- Enabled sharing custom rules, commands, and prompts with the entire team via deeplinks.(2.0)
- Enabled Enterprise teams to distribute hooks directly from the web dashboard, including managing drafts and OS targeting.(2.0)
- Enabled viewing a timestamped Audit Log of admin events including user access, setting changes, and team rule edits.(2.0)
All AI Bug Fixes
- Fixed terminal interaction bugs within the agents window, including issues with editing shortcuts and approval/overlay edge cases.(3.3)
- Fixed several regressions affecting the slash menu and input approval workflows.(3.3)
- Fixed MCP authentication edge cases, specifically transient 401 errors and stale credential handling.(3.3)
- Fixed issues related to multi-repo environment selection and caching.(3.3)
- Fixed various cloud agent timing and hydration edge cases that previously impacted reliability.(3.3)
- Fixed text area behavior for Network Access Controls so pressing Enter reliably adds a newline at the end of the input.(3.0)
- Fixed hooks loading so multi-root workspaces correctly read project hook files from all workspace folders instead of only the first one.(3.0)
- Fixed a markdown parsing bug where parenthesized HTTP(S) links could be misread as citations.(3.0)
- Fixed todo card visibility to prevent them from disappearing after all todos complete.(3.0)
- Fixed Composer queued prompts that were not resuming automatically after editing operations.(3.0)
- Fixed picker behavior for disabled but selectable models by removing misleading styling and auto-enabling the model upon user selection.(3.0)
- Fixed a bug where expanding/collapsing thinking blocks didn't work while streaming was still in progress.(3.0)
- Fixed a bug where Shift+Enter line breaks weren't treated as multiline content, preventing the prompt input field from staying in an incorrect state.(3.0)
- Fixed 11 unspecified bugs (as noted in the release notes summary).(2.4)
- Fixed unspecified bug fixes related to CLI operations.(CLI)
- Fixed file conflicts when running multiple agents in parallel by using isolated environments.(2.0)
- Fixed memory leaks and improved overall memory usage across the application.(2.0)
- Improved quality when working with Agent across all models, especially GPT-5 Codex, due to harness improvements.(2.0)
Releases with AI Changes
05-19-263 featuresThis release introduces a major integration with Jira, allowing users to initiate cloud agent tasks directly from Jira work items by assigning them or using the @Cursor mention. Cursor uses ticket context to scope work and posts completion updates, including PR links, back into Jira.
composer-2-53 featuresComposer 2.5 is now available, representing a substantial upgrade in intelligence and reliability for complex, long-running tasks. This version is designed to be more pleasant to collaborate with and follows intricate instructions more consistently. The release also details updated pricing tiers for the Standard and Fast model options.
microsoft-teams3 featuresThis release introduces deep integration with Microsoft Teams, allowing users to delegate tasks directly from Teams channels using the @Cursor mention. The AI agent is now smarter, automatically selecting the correct repository and model, and using the full conversation history for better context before generating solutions.
3.35 features5 fixesThis release delivers a major overhaul to the PR review workflow, integrating creation through merge into one place with enhanced views for threads, commits, and changes. Performance is significantly boosted by enabling parallel execution of plan steps using async subagents. Additionally, users gain new productivity features like splitting changes into multiple PRs and pinning favorite skills as quick actions.
05-04-267 featuresThis release focuses heavily on Enterprise administration, introducing granular model access controls and new soft spend limits with intelligent usage alerts. Admins also benefit from an updated usage analytics tab with enhanced filtering options for better oversight.
sdk-release4 featuresThis release introduces the powerful Cursor SDK, enabling users to build custom agents accessible via TypeScript across the desktop, CLI, and web apps. The Cloud Agents API has also been significantly reworked to support durable agents with improved run scoping, streaming, and standardized response formats.
3.010 features8 fixesCursor 3 introduces the powerful new Agents Window, enabling users to run multiple agents in parallel across various environments with improved visibility and control. This release also adds Design Mode for precise UI targeting and Agent Tabs for managing multiple chats simultaneously. Several usability improvements focus on performance, such as faster large-file diff rendering, alongside key bug fixes across input handling and workspace loading.
2.45 features1 fixThis release significantly enhances agent capabilities by introducing Subagents for parallel, specialized task execution and enabling direct image generation within the agent interface. Additionally, Enterprise users gain Cursor Blame for detailed AI attribution tracking, and agents can now proactively ask clarifying questions during complex workflows.
CLI4 features1 fixThis release significantly enhances the Command Line Interface (CLI) by introducing new controls for managing models, rules, and MCP servers directly via new slash commands and flags. Users can now list models, manage rules, and toggle MCP servers on the fly, alongside notable performance improvements for CLI hooks.
2.12 featuresThis release introduces powerful new capabilities including AI Code Reviews directly in the editor for immediate bug detection and Instant Grep (Beta) for lightning-fast codebase searching. Plan Mode has also been enhanced with interactive question-answering to improve plan quality.
2.012 features3 fixesThis release introduces significant new capabilities, including the Multi-Agents editor for running up to eight agents in parallel and the new, faster Composer coding model. Key stability improvements include Sandboxed Terminals going GA on macOS and major performance boosts for Language Server Protocols. Users can now also control the agent via Voice Mode and define centralized Team Commands.