> ## Documentation Index
> Fetch the complete documentation index at: https://netter.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Build a pipeline

> Build your first pipeline by describing what you want in plain English. The AI Architect proposes the step DAG and you iterate.

A **pipeline** is a directed graph of **steps** that fetch, transform, and write data, optionally surfacing the result as a database or dashboard. You build pipelines inside a **project**.

## Before you begin

* A project to work in (create one from **Projects → New project**).
* At least one connected integration if your pipeline starts from an external API. See [Integrations](/docs/integrations/overview).

## Steps

<Steps>
  <Step title="Open the AI Architect">
    From your project, start a new chat. The Architect splits the screen: chat on the left, workflow graph on the right.
  </Step>

  <Step title="Describe what you want">
    Type what the pipeline should do in plain English—for example, "Pull new Stripe invoices every hour, flag the ones above \$10k, and write them to a dashboard."

    The Architect proposes a step DAG with the right step types and pre-coded operators wired together.
  </Step>

  <Step title="Iterate on the graph">
    Review the proposed steps. Ask the Architect to add, remove, or reconfigure steps. Each step in the graph shows its type, operator, and parents.

    See [Step types](/docs/pipelines/step-types) for what each role does and where it can sit in the DAG.
  </Step>

  <Step title="Deploy">
    When the graph is right, deploy the project. Deploy creates the runtime resources (databases, dashboards) and makes the pipeline runnable.
  </Step>

  <Step title="Run it">
    Trigger the pipeline with **Run all** from the project page, or attach a schedule to a database step so it refreshes on a cron. See [Runs](/docs/pipelines/runs).
  </Step>
</Steps>

## Next steps

* Understand the [step types](/docs/pipelines/step-types) and what they're allowed to do.
* Pick the right [operators](/docs/pipelines/operators) for ingest, transform, AI, and storage.
* Configure [triggers](/docs/pipelines/triggers) for scheduled and cascade refreshes.