Back to JetBrains

Hands-On Air with Dmitry Jemerov and Grigorii Kargin

JetBrainsMay 7, 20261h 5m
Topics54
Welcome and Introduction0:09Installation and Platform Availability2:01Multi-Subscription Support4:02Onboarding and Environment Options4:49Code Review Philosophy5:31Project Structure6:30IDE Features and Philosophy9:00Claude.md Initialization10:31Frontend and Backend Execution11:36Dictionary Filtering Task13:02Task-Specific Change Visibility16:01Code Navigation Features17:03Agent Code Review19:32Filtering Implementation Results22:01Parallel Tasks and Worktrees25:01Attestations Linking Task26:01Review Comments and Agent Fixes29:00Team AI Usage32:02Valuing Product Over Code33:08Architecture and Code Quality Priorities34:00Balancing Clean Architecture with Iterative Development35:02AI Plan Generation and Prompt Issues35:31Model Selection and Memory36:30Work Tree Implementation37:00Agent-Generated Changes and False Positives38:00Interactive Agent Questions39:00Typical Agent Workflow Experience39:32Bash Command Approval and Work Tree Tasks40:00Sandbox Security and State Management41:00Git Integration Quality42:01Work Tree Build Issues43:00Plan Detection and Work Tree Completion44:02Working Copy Limitations45:00Web Version Preview45:30WebAssembly Implementation46:31Web Version Features47:31Public Preview Reliability Discussion48:01Nightly Build Philosophy49:00Air vs IntelliJ Use Cases49:30Air vs CLI Comparison51:00Historical Parallel52:32Performance Comparison Issues53:00Agent Integration Differences54:01Vim Mode Consideration54:30Subscription and API Integration55:01Juni Integration56:01Technical Implementation Details57:00Cloud Containers Timeline58:00ACP Protocol Explanation58:32Rich Interaction Benefits59:02User Success Stories Contest59:30Final Code References1:04:08Contact Information1:04:30Closing Remarks1:05:01
In a Nutshell

Dmitry Jemerov and Grigorii Kargin demonstrate JetBrains Air, a new agentic development environment that runs AI agents (Anthropic, OpenAI, Google, Juni) in isolated workspaces or Docker containers while retaining IDE navigation and search features for code review. The core workflow centers on plan mode for complex tasks, agent-generated code review by a second agent, and worktrees for parallel development, with the team stressing that reviewing AI-generated code remains essential for maintainable projects. Air is currently Mac-only with Windows/Linux and ACP support planned for May, positioning it as the preferred tool when agents handle 80% of coding versus traditional IDEs for manual editing.

AI-Generated Notes

These notes were generated by AI and may contain inaccuracies.

Dimitri hosts the live stream with Grigori Kargin, team lead of Air at JetBrains. Grigori has worked at JetBrains on multiple IDEs and previously on Kotlin. He is currently studying linguistics at the University of Leiden and has been working on a linguistic database project. He is exploring JetBrains' AI development tools.

Grigori explains that Air is an agentic development environment centered around agent experiences. It is agent agnostic and supports agents from Anthropic, OpenAI, Google, and JetBrains' own agent Juni. ACP support is planned to allow any ACP-compatible agent.

The installation is performed through Toolbox. Air is currently available on Mac, with Windows and Linux internal builds ready and planned for release in May. ACP support will appear in the nearest build under a feature flag, with full marketplace support coming.

Users can use multiple subscriptions simultaneously, including JetBrains AI, OpenAI, and Anthropic keys. This allows using both cloud agents and local agents together.

Air presents an onboarding walkthrough. Environment options include local workspace, Git worktree, and Docker. Local workspace uses the main copy of the project, while Docker provides isolation for running multiple application instances without conflicts.

Reviewing AI-generated code is emphasized as essential. For code that will persist in a project, understanding the structure prevents confusion when issues arise. This differs from one-off scripts where review may be optional.

Sign in to read the full notes

Get access to AI-generated notes, topic timestamps, and more.