AI-native development environment
How to use
TRAE.
Building and modifying applications through an AI-native editor while keeping project context, generated plans, agent actions, and visual previews in one workspace.
TRAE is a AI-native integrated development environment with conversational and agentic coding workflows. Building and modifying applications through an AI-native editor while keeping project context, generated plans, agent actions, and visual previews in one workspace. 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 TRAE
Get into the official TRAE experience with the right account and a setup you understand.
- 01
Start at https://www.trae.ai/ and confirm the domain before entering account or payment information.
- 02
Availability: TRAE is distributed as a desktop AI IDE with code completion, chat, project context, agent and builder workflows, model access, and extensions.
- 03
A supported desktop system, a TRAE account where required, an authorized repository, and an organizational decision on code indexing, telemetry, data regions, models, and extensions.
- 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 TRAE session
Learn the interaction loop using a small task with a clear outcome.
- 01
Review the current privacy policy and data-practices statement before installing or opening confidential code.
- 02
Enable the strictest suitable privacy settings and start with a disposable or non-sensitive repository branch.
- 03
Give one bounded task clear acceptance criteria, relevant files, prohibited actions, and validation commands.
- 04
Review network-sensitive features, generated files, commands, tests, preview behavior, and the complete diff before shipping.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of TRAE 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 TRAE 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.
- TRAE states that codebase files may be temporarily uploaded to compute indexes and that embeddings and metadata can be retained. Privacy Mode can limit telemetry but does not replace an organizational data review. Avoid regulated or confidential repositories until terms, regions, subprocessors, retention, model training, and deletion meet policy; minimize context and extensions, isolate agent work, keep credentials out, and verify every command, dependency, diff, and deployment manually.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use TRAE for the work it does best.
Each workflow is a separate guide with its own steps and review checkpoints.
Test coding quality, network behavior, indexing, telemetry controls, and reviewability before organizational adoption.
↗ 02 WorkflowBuild a controlled application change in TRAEUse the AI-native editor for one bounded feature while keeping context, commands, credentials, and release authority constrained.
↗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.