Safety & Control

Permission mode

The agent-level setting that decides whether tool calls run automatically, require human approval, or are blocked — with per-tool overrides taking precedence.

A permission mode sets the default posture for how an agent's tool calls are resolved. Every call is resolved to allow, ask, or deny before it executes.

The four modes

ModeBehaviour
always_askEvery tool call requires human approval (read-only built-ins exempt)
ask_for_actionsRead-only tools run automatically; anything with side effects asks first
autonomousEverything runs except an explicit per-tool ask/deny override
tools_disabledNo tools or skills available to the run at all

The precedence ladder

Mode is the default, not the final word:

  1. Per-tool overrides always win. An explicit deny blocks the call; an explicit ask requires approval even in an otherwise fully autonomous agent.
  2. Read-only built-in platform tools are never gated. They always run.
  3. A destructive or open-world-acting tool generally requires approval unless the mode or an explicit per-tool allow says otherwise.
  4. Unrecognised modes or risk classes fail closed to ask — never silently to allow.

Choosing a mode

Pick autonomous for unattended, scheduled, or agent-to-agent runs. Then use per-tool ask/deny overrides for the specific tools you want gated, rather than dropping the whole agent to always_ask.

That combination — autonomous mode plus targeted overrides — expresses "run freely except for these three dangerous things", which is almost always what production actually needs.

The pitfall

Expecting an ask-gated tool to work on an unattended run. There is no approver present, so it is denied — not silently allowed, and not left pending forever. See fail-closed. Design unattended paths with a non-interactive fallback, or they will simply stop at that tool.

In the Anter docs

Related terms

Last updated July 27, 2026