Skip to main content

Tools

When you describe a task in chat, the agent does not guess — it uses tools to work on your project: search the codebase, read and edit files, run tests, or reach a connected app. Each action shows up in the conversation so you can follow along.

Think of tools as the agent's hands: scoped to your workspace, useful for real engineering work, and paused when something needs your OK.

What are tools

Tools are the actions the agent can take on your behalf. You write the goal in plain language; the agent chooses the right steps. Most steps run automatically. Steps that could change your project, run risky commands, or reach the network wait for your approval first.

You do not pick tools manually — you describe the outcome, and the agent handles the rest.

What the agent can do

When you ask for…What happens
Fix a failing testThe agent finds the relevant files, reads the failure, runs your test command, and applies a fix
Build or change a featureIt searches the repo, edits the files that matter, and can run lint or build checks
Understand unfamiliar codeIt explores the codebase and explains structure, dependencies, and behavior
Work with your stackWith plugins installed, it can use issue trackers, observability tools, databases, and other services your team connects

Those actions map to a few built-in areas:

AreaWhat it helps with
CodebaseFind, read, and edit files in the project you opened
TerminalRun builds, tests, linters, and Git commands in your workspace
WebLook up public documentation or check web behavior when the task needs it
IntegrationsTalk to connected apps through plugins your organization enables
Session helpersBreak large tasks into steps and load plugin skills for domain-specific work

On cloud agents, the same capabilities apply in a remote environment. What the agent can reach on the network follows your organization's security settings.

Approvals

When the agent wants to do something sensitive, you see a prompt in chat before it runs — for example a file edit outside normal paths, a destructive shell command, a push to a remote, or a call to an external integration.

  1. Review what the agent proposed — the command, file path, or integration call
  2. Approve or deny — if you deny, the agent can try a safer approach
  3. Allow for session (optional) when you trust a repeat action, such as running your test suite
You stay in control

Routine reads and safe edits often proceed without interrupting you. Anything that crosses a trust boundary — deletes, pushes, credentials, or unfamiliar integrations — stops for your decision.

Review before you approve

Read terminal commands carefully, especially deletes, remote pushes, and anything touching credentials or global system state.

Extensions

Your team can extend what the agent can do by installing plugins from the marketplace — integrations, skills, and optional automation for how you already work. Administrators set org-wide limits in Model control and Agent security.