Agent Modes (Modes)

Several agent modes are available.

Agent Mode

A full-fledged agent that can read and edit files. Best suited for day-to-day work not related to project exploration and testing.

Ask Mode

Read-only agent mode: it can read files in the project and pages on the internet. Best suited for project exploration tasks (e.g., onboarding into a new project), brainstorming implementation ideas, analyzing the causes of bugs.

Test Mode

A mode focused on test generation. Although you can generate tests in Agent mode, this mode provides better results.

For example, on our internal benchmark of 33 real projects (with endpoints of ~2000 lines, ≥150 KLOC with Spring, TestContainers, Java, Kotlin) with all other things being equal (same model and same input prompt) the Test agent gave significantly better results than the basic Agent.

Test generation task from source code	Agent	Test
Percentage of compiled test classes	76%	94%
Percentage of passing tests	67%	90%
Test coverage	64%	80%

The Test mode is currently only available in IDEA (and its forks) for Java and Kotlin.

Plan Mode

The mode shows a detailed plan of steps for the request and lets you edit it while working. It is useful when you need to align the sequence of actions before a complex task — for example, migrating to a new framework version or creating a microservice from scratch. The plan is split into subtasks with acceptance criteria and saved in the repository as a set of files, so other team members can discuss it.

Review Mode

The mode can only read files, so it is safe by default. It is useful for checking changes made by the agent or another person. For code, the Review agent can run anti-pattern checks, such as verifying that the code does not use try/catch on a base exception type (for example, Throwable). The mode uses IDE inspections to highlight potential issues in the code and reduce the risk of accumulating tech debt.

Debug Mode

The mode allows the agent to control the IDE debugger — set breakpoints, run code with the debugger, and analyze variable state.

This enables advanced debugging techniques:

• scientific debugging (step-by-step hypothesis checking);
• adding temporary logs with subsequent removal;
• running tests with debugging to analyze specific crash scenarios.

This is useful when you've encountered a complex bug that's difficult to diagnose from logs and code analysis alone, and you need to "look inside" program execution to understand what's happening.

Custom agent modes

You can create your own agent modes through the button in the agent selection menu. This lets you set up an agent for a specific task, such as a technical writer for documentation. In such an agent, you can explicitly define the available tools and the list of preinstalled Skills to focus it on a specific scenario (for example, security or documentation).

We support a subset of the Claude agents format, so you can take any Claude agent and use it without changes. Support for the format will be expanded in upcoming releases.