How JetBrains AIR Reinvents IDEs with Built‑In AI: A Hands‑On Guide

AIR Overview

JetBrains AIR is a brand‑new, standalone IDE built from the ground up with AI as the default workflow rather than an optional add‑on, aiming to make AI‑assisted programming a core part of the development experience.

AI is the default workflow, not a toggle.

Emphasis on determinism and explainability to avoid “black‑box” magic.

Developers retain full control over code.

Getting Started in Three Steps

1. Install and First Run

Currently available only on macOS (Windows/Linux planned for 2026). After installing, log in with a valid subscription account to reach the welcome screen.

2. Open a Project

Two ways to open a project:

Open a local folder via the Open button.

Clone from Git by selecting Clone from Git and providing the repository URL and destination path.

When a project is opened for the first time, AIR asks whether to trust the code:

Preview : limited functionality, cannot execute code.

Trust : allows code execution (recommended only for trusted projects).

3. Define a Task

Interact with the AI agent in chat mode to gradually clarify the task. Provide a clear description (e.g., “Add pagination to the order module, 10 items per page”) and optional context such as a file path src/orders/service.py. AIR also supports a “plan mode” where the AI first generates an execution plan before refining the task.

Task configuration includes execution environment, AI model, and permission mode.

Permission modes:

Ask permission: prompts on first use of a tool.

Auto edit: automatically accepts file edits.

Plan mode: only analyses code, no edits or execution.

Full access: skips all permission prompts.

Ways to add context to a task:

Files and folders

Git branches / commits / local changes

MCP servers

Terminal tabs

Upload local files

4. Run and Manage Tasks

Task states include:

Running – AI is executing, you can add input.

Waiting for user action – AI pauses, awaiting manual intervention.

Finished – task completed, ready for review.

Canceled / Archived – manually stopped or archived after exit.

Multiple tasks can run in parallel without interfering with each other.

5. Review and Commit Changes

In the Review tab, use the diff panel to inspect AI‑generated modifications:

Unified diff – side‑by‑side comparison on a single page.

Split diff – left/right column comparison.

You can also click the icon next to a line number to add comments, just like a code review.

6. Advanced: MCP Server Integration

Model Context Protocol (MCP) lets AIR connect to external tools such as databases or APIs. Add a JSON configuration to enable a server.

Path in settings:

Settings → AI → MCP Servers

{
  "mcpServers": {
    "alphavantage": {
      "command": "uvx",
      "args": ["av-mcp", "YOUR_API_KEY"]
    }
  }
}

Example: connecting to the Alpha Vantage API.

Conclusion

JetBrains AIR lowers the barrier to AI‑assisted development through a clear workflow: define the task with context, configure execution environment and permissions, then review and submit changes. Combined with parallel task execution, MCP extensions, and local snapshots, AIR provides an efficient, controllable AI development experience.