# Quickstart: agent

> Create an agent task with a goal, an OpenWAF Egress target, a model and a step budget, and review what it proposes.

An `agent` task has no code of yours. Our agent loop drives the browser toward a **goal** you write, with the **model** you choose, called through [OpenWAF Egress](https://developers.openwaf.dev/egress/cloud/get-started/). Like a script, it can read freely and can only propose writes.

## Before you start

- **Access** to OpenWAF Tasks and a browser key. See [get access](https://developers.openwaf.dev/tasks/#get-access).
- **OpenWAF Egress** enabled, with a provider credential on the target you will use, for example `openai`. See [targets and keys](https://developers.openwaf.dev/egress/cloud/targets-and-keys/).
- **An organization-wide `admin`**.

## 1. Create the task

| Field | Meaning |
|---|---|
| `agent.goal` | What to do, up to 4000 characters. Say what to read, what to report and what, if anything, to propose. |
| `agent.egress_target` | The Egress target the model calls go to; it must have a credential |
| `agent.model` | The model name at that target |
| `agent.max_steps` | Tool calls of the agent per run, 1 to 50 (default 25) |
| `allow` | Domains the browser may visit |

```sh
curl -sS -X POST "https://dash.openwaf.dev/v1/orgs/$ORG/tasks" \
  -H "Authorization: Bearer $OPENWAF_TOKEN" -H "Content-Type: application/json" \
  -H "X-Change-Reason: Weekly docs review" \
  -d '{"name": "docs-review", "kind": "agent",
       "schedule": {"cron": "0 8 * * 1", "timezone": "Europe/Madrid"},
       "browser": {"key_id": "'$KEY_ID'", "profile": "", "recording": true},
       "allow": ["example.com", "*.example.com"],
       "agent": {"goal": "Open https://example.com/docs/ and its linked pages. Report broken links and pages that contradict each other as the output. Do not propose any action.",
                 "egress_target": "openai", "model": "gpt-4.1-mini", "max_steps": 30},
       "max_run_minutes": 15}'
```

OpenWAF creates an Egress agent for the task, named `task-` and 8 hex digits (`egress_agent` in the task). Its calls appear in the [Egress events](https://developers.openwaf.dev/egress/cloud/agents/) like those of any other agent.

## 2. What the agent can do

The agent sees the page as text and screenshots and uses these tools: navigate, click, type, read, take a screenshot, log, set the output, and `propose_action`. `propose_action` takes the same `summary`, `target` and `steps` as a script's [`task.approve`](https://developers.openwaf.dev/tasks/approvals/#steps). It can propose up to 5 actions per run.

Page content reaches the model marked as untrusted data, and the model is told never to follow instructions from pages. Even if it did, it cannot write: see [prompt injection](https://developers.openwaf.dev/tasks/security/#prompt-injection).

## 3. Run it and review

Run it now (`POST /v1/orgs/{org}/tasks/{task}/run`) and open the run: logs, screenshots, `output`, `model_calls`, `prompt_tokens` and `completion_tokens`. If it proposed an action, review it in **Tasks → Approvals** as in the [script quickstart](https://developers.openwaf.dev/tasks/quickstart-script/#approve-it).

A run stops when the agent finishes, after `max_steps` tool calls or after `max_run_minutes`, whichever comes first (`timed_out` for the last one).