The outcome

Produce a tested implementation whose commands and file access remain understandable and reversible.

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 narrows that broad capability into one repeatable outcome, with checkpoints that keep the source material and your judgment in the loop.

Before you begin

Set the boundary before the tool starts.

Choose one real task, identify who will use the result, and decide what evidence or test will make the result acceptable. Gather only the source material needed for that task. If the work contains confidential, personal, regulated, or client-owned information, confirm that the platform and account are approved before sharing it.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

Step by step

A workflow you can repeat.

  1. 01

    Open a clean Git branch, inspect project-level .junie configuration and guidelines before granting trust, and record baseline tests.

  2. 02

    Start in ask or plan mode and provide the outcome, acceptance criteria, relevant paths, constraints, non-goals, and required validation.

  3. 03

    Review the plan, keep Brave mode off, and allowlist only exact safe diagnostics rather than broad command, MCP, or outside-project categories.

  4. 04

    Supervise implementation, especially build-script edits, dependencies, external paths, MCP calls, credentials, hooks, and requests for wider permissions.

  5. 05

    Run trusted checks, inspect the complete diff, use Junie's local review as additional evidence, and send the result through ordinary peer review.

Working standard

What good use looks like.

  • Review configuration before project trust.
  • Prefer exact allowlist rules.
  • Treat local review as evidence, not approval.

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.

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 collection.