# Your first flow

> Create your first flow, reuse prompts with templates, follow and steer the agents while they work, and download the report at the end.

A **flow** is one run of PentAGI: a goal, the [tasks](https://pentagi.com/docs/glossary/#task) created from your messages, and everything the [agents](https://pentagi.com/docs/glossary/#agent) did along the way.

## [Create a flow](https://pentagi.com/docs/getting-started/first-flow/#create-a-flow)

![The new flow form](https://pentagi.com/images/product/new-flow.webp)

1. Open **Flows** in the sidebar and click **New Flow**.
2. Choose a mode:

   * **Automation** — PentAGI carries out the goal end to end on its own.
   * **Assistant** — an interactive conversation you steer step by step. Turn on **Use Agents** to let the [assistant](https://pentagi.com/docs/glossary/#assistant) delegate [subtasks](https://pentagi.com/docs/glossary/#subtask) to specialized agents.
3. Pick the LLM [provider](https://pentagi.com/docs/glossary/#provider) for this [flow](https://pentagi.com/docs/glossary/#flow).
4. Describe the target and the objective in natural language.

A good first prompt names the target, the kind of assessment, the scope limits and the result you expect:

```text
Assess https://target.example for common web application vulnerabilities.
Focus on authentication, file handling, and injection issues. Stay within the
provided target only and summarize confirmed findings with reproduction steps.
```

> [!WARNING]
> Only test systems you own or are explicitly authorized to assess.

## [Reuse prompts with templates](https://pentagi.com/docs/getting-started/first-flow/#reuse-prompts-with-templates)

The new-flow form has a [template](https://pentagi.com/docs/glossary/#template) picker that prefills the message from a saved template in **Templates**. Templates are plain natural language — no special syntax is required.

## [Follow the work](https://pentagi.com/docs/getting-started/first-flow/#follow-the-work)

PentAGI opens the flow page as soon as the flow starts:

* **Automation** shows the agents' messages and progress; **Assistant** is a chat with the same [tools](https://pentagi.com/docs/glossary/#tool), and **Dashboard** breaks usage down by model, [agent type](https://pentagi.com/docs/glossary/#agent-type) and function.
* **Tasks** lists the plan — tasks and subtasks with their status.
* **Terminal** streams every command and its output from the [sandbox](https://pentagi.com/docs/glossary/#sandbox).
* **Agents**, **Searches** and **Vector Store** show delegation, web research and [memory](https://pentagi.com/docs/glossary/#memory) lookups.
* **Files** holds uploads, attached resources and files pulled from the container, and **Screenshots** keeps screenshots of the pages the agents opened.

![A running flow: agent messages on the left, the plan of tasks and subtasks on the right](https://pentagi.com/images/product/flow-tasks.webp)

![Every command and its output from the sandbox in the Terminal tab](https://pentagi.com/images/product/flow-terminal.webp)

## [Steer a running flow](https://pentagi.com/docs/getting-started/first-flow/#steer-a-running-flow)

Open the **Assistant** view of the same flow to check its state, stop the current task, send follow-up instructions or adjust the remaining planned subtasks — without restarting the flow.

## [Get the report](https://pentagi.com/docs/getting-started/first-flow/#get-the-report)

Use the **Report** menu on the flow page to open the [report](https://pentagi.com/docs/glossary/#report) on the web, copy it, or download it as Markdown or PDF.

> [!NOTE]
> Start with a narrow target and a single clear objective. Short, focused flows are easier to review and help you refine prompts before larger flows.