How JetBrains AIR Transforms IDEs with Built‑in AI: A Hands‑On Guide

What is JetBrains AIR?

JetBrains AIR is a brand‑new independent IDE built from the ground up, where AI is the default workflow rather than an optional add‑on. Its core principles are AI‑first, deterministic and explainable behavior, and developers retain full control over the code.

AI is the default workflow, not an optional enhancement

Emphasizes determinism and explainability, avoiding "black‑box" magic

Developers always keep the primary authority over code

Quick Start: Three Steps to Experience AIR’s AI‑Native Workflow

1. Install and First Run

Currently only macOS is supported; Windows/Linux versions are planned for 2026. After installing, sign in with a valid subscription account to reach the welcome page.

2. Open a Project

Two ways to open a project:

Open a local folder: click Open and select the project directory.

Clone a Git repository: click Clone from Git , enter the repository URL and the local path.

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

Preview : limited functionality, code cannot be executed.

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

3. Define a Task

Interact with the AI agent in chat mode, providing a clear task description (e.g., "Add pagination to the order module, 10 items per page") and optional context (e.g., "reference src/orders/service.py").

Supports Plan mode , where the AI first generates an execution plan before refining the task.

Task configuration includes permission modes:

Ask permission: prompts the first time a tool is used.

Auto edit: automatically accepts file edits.

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

Full access: skips all permission prompts.

Context can be added via:

Files and folders

Git branches / commits / local changes

MCP servers

Terminal tabs

Uploaded local files

Code snippets can also be selected directly and added to a task.

Running and Managing Tasks

Task states include:

Running : AI is executing; you can add input at any time.

Waiting for user action : AI pauses and requires manual intervention.

Finished : Task completed; you can review the changes.

Canceled / Archived : Manually stopped or exited, then archived.

Multiple tasks can run in parallel (e.g., one writing tests while another fixes a bug) without interference.

Review and Commit Changes

In the Review tab, use the diff panel to examine AI‑generated modifications. Two view modes are available:

Unified diff: side‑by‑side comparison of old and new code.

Split diff: left‑right column comparison.

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

Advanced Feature: MCP Server Integration

Model Context Protocol (MCP) lets AIR connect to external tools such as databases or API services. Configuration is done by pasting a JSON snippet into 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 for human‑AI collaboration by embedding AI directly into the IDE. Its clear workflow consists of defining tasks with context, configuring execution environment and permissions, and reviewing & committing changes, while supporting parallel tasks, MCP extensions, and local snapshots for an efficient, controllable AI‑driven development experience.