JetBrains coding agent
How to use
Junie.
Exploring a codebase, producing an implementation plan, making supervised changes, and reviewing local or pull-request diffs with durable project guidance.
Junie is a JetBrains coding agent for IDE, terminal, and automated review workflows. Exploring a codebase, producing an implementation plan, making supervised changes, and reviewing local or pull-request diffs with durable project guidance. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.
AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.
Access & setup
Find, install, and sign in to Junie
Get into the official Junie experience with the right account and a setup you understand.
- 01
Start at https://www.jetbrains.com/junie/ and confirm the domain before entering account or payment information.
- 02
Availability: Junie is available in supported JetBrains IDEs and as a cross-platform CLI, with interactive planning, implementation, debugging, local review, and headless workflows.
- 03
A supported JetBrains IDE or Linux, macOS, or Windows terminal; an approved repository; JetBrains, Junie API key, or supported BYOK authentication; and reviewed project trust and action settings.
- 04
Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.
- 05
Run one low-risk test task before connecting sensitive files, repositories, or workspace data.
- Use official download pages.
- Review permissions during setup.
- Keep installers and applications updated.
First session
Your first useful Junie session
Learn the interaction loop using a small task with a clear outcome.
- 01
Open a clean Git branch, keep an unfamiliar project untrusted until its configuration is reviewed, and record baseline checks.
- 02
Start in ask or plan mode and give Junie the outcome, acceptance criteria, relevant paths, constraints, and non-goals.
- 03
Review the proposed plan, keep Brave mode off, and approve only the exact commands, MCP tools, and external paths required.
- 04
Inspect every changed file, run trusted tests, use local review for a second pass, and release only through normal peer review.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of Junie output
Turn generated code into a change you would put your name on in review.
- 01
Restate the intended behaviour and the acceptance criteria before reading a single generated line.
- 02
Read the diff rather than the chat summary; the summary describes intent, the diff describes what actually changed.
- 03
Run the test suite, then write a test that would fail if the change were wrong, and confirm it passes for the right reason.
- 04
Check the edges the model tends to skip: error paths, null and empty cases, concurrency, and migration or rollback behaviour.
- 05
Trace every new dependency, network call, and file write, and confirm each one is genuinely required.
- Review the diff, never the description of the diff.
- A passing test suite proves the tests pass, not that the change is correct.
- Keep changes small enough that a human can actually review them.
Privacy & permissions
Use Junie safely
Give the tool enough repository access to help, and no more than that.
- 01
Decide what the tool may read and what it may write before connecting a repository.
- 02
Scope tokens and integrations to the narrowest repository, branch, and permission set that still works.
- 03
Keep secrets out of the context window: use environment variables and secret stores, never inline credentials.
- 04
Require review before generated code touches authentication, payments, permissions, migrations, or deletion paths.
- 05
Audit what the integration retained after the session, and revoke access that is no longer needed.
- Junie can edit files, run terminal commands, invoke MCP tools, read or write outside a project, load project configuration, and operate headlessly. Brave mode removes approval gates; broad regular expressions and action-type rules can authorize much more than intended; build-script edits may execute code. Review project trust, `.junie` configuration, `.aiignore`, guidelines, hooks, credentials, provider terms, and every allowlist rule before consequential work.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use Junie for the work it does best.
Each workflow is a separate guide with its own steps and review checkpoints.
Use project trust, plan mode, approvals, and local review to turn a request into a controlled code change.
↗ 02 WorkflowConfigure governed Junie guidance and review automationStandardize project context and automated review without letting repository configuration silently gain excessive authority.
↗Official references
Check the current product documentation.
Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.