---
title: "Auto Mode: dangerous action checks for AI agents | Astroware"
description: "Auto Mode checks each action an AI agent is about to take, and blocks a dangerous one or flags it for a person to approve."
url: https://astroware.ai/auto-mode
language: en-GB
---
**Auto Mode** Live

# Dangerous action checks for AI agents.

Auto Mode is like Claude Code Auto Mode but for all agents.

Checks each action an AI agent is about to take, and blocks a dangerous one or flags it for a person to approve.

[Read the API docs](https://astroware.ai/docs/eu-mode) [Book a call](https://calendar.app.google/6S2eq9HLADdrN8Ct9)

Auto Mode is part of EU Mode. [The full EU Mode page](https://astroware.ai/eu-mode)

**Status**

Live

**Starts in**

Shadow mode

**Model**

eu-mode

**Price**

$30 / billion input tokens Output tokens are free.

What it does

## Checks each action an AI agent is about to take

Your agent An action it is about to take

Auto Mode Checks each action

block flag for a person to approve

Shadow mode

## Every key starts in shadow mode

It reports what it would have decided and blocks nothing, until you switch the key to enforce in the console.

The API

## How to call it

- A person at your company signs in to the console and creates a key. The key is shown once.
- POST https://api.astroware.ai/v1/chat/completions, with the header Authorization: Bearer <key>.
- Set "model" to "eu-mode". The same endpoint, key and price as HaloGuard EU; only the model name differs.
- $30 / billion input tokens. Output tokens are free on all models. Tokens of your text are counted each time they go through a model: text sent to two models, or through two checks in eu-mode, is counted twice.

Read the [EU Mode API docs](https://astroware.ai/docs/eu-mode) before the first call.