Chat (IDE)

Agent modes & personas

The agent is a real tool-calling loop that reads, searches, and edits your codebase and runs whitelisted commands. How much it does without asking you first is controlled by its mode.

Agent modes

ModeBehaviorBest for
InteractiveEvery file edit and command is shown for approval before it runs.Unfamiliar code, high-stakes changes, code review-style sessions.
BypassFile edits apply automatically. Whitelisted commands still run without a prompt; anything not whitelisted still asks.Routine work where you trust the edit but still want a command safety net.
AutopilotThe agent runs a full multi-step task end-to-end with minimal interruption.Well-scoped tasks you're comfortable delegating fully — e.g. "add tests for this module."

You can switch modes mid-session from the tool window — there's no need to restart a chat to change how much autonomy the agent has.

Named personas

Type @ in the chat box to invoke a specialist persona — each one carries a tuned prompt and a scoped set of tools for its job:

PersonaFocus
@debuggerRoot-cause analysis, reading stack traces, inspecting live debugger state.
@testWriting and running tests, reading structured pass/fail results.
@securitySecurity review of the selected code or change.
@reviewCode review pass — style, correctness, edge cases.
@docsWriting or updating documentation and comments.
@refactorRestructuring code without changing behavior.
@modernizeUpgrading patterns, APIs, or language features to current idioms.
@profilerInvestigating performance issues.
@gitGit operations — history, blame, commit/branch help.
@planBreaking a larger task down into a step-by-step plan before executing.

Standard unlocks the full built-in set above. Pro adds the ability to define and save your own custom personas with a tailored prompt and tool scope.

Multi-agent delegation

Mid-turn, the primary agent can hand a focused sub-task off to a specialist persona — for example, delegating root-cause analysis to @debugger while it keeps working on the rest of the change — running several delegated calls in parallel when it helps. Standard allows up to 3 delegated calls per turn (2 in parallel); Pro and Teams raise that to 8 (8 in parallel).

Resilient runs

The agent loop runs server-side, so a dropped connection doesn't lose progress — it resumes mid-turn instead of restarting. Tool execution itself (reading files, applying edits, running commands) still happens locally in your IDE, where your code lives.