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

# Introduction

> Director turns a URL and one sentence into a polished product demo video — driven by a real browser, not a template.

Director is **the demo agent**: give it a URL and one sentence, and it operates your product in a real browser, records the session, and renders a polished demo video — auto-zoom, smooth cursor motion, captions, fades — with no manual editing.

It's built agent-first. The primary caller is expected to be an AI agent (Claude Code, Cursor, a CI bot, your own automation) rather than a human clicking through a dashboard, so every interface returns structured, machine-actionable results: a verified `goalMet` outcome, not just a video link.

## How it works

<Steps>
  <Step title="Brief">
    You send an instruction (`"Sign in and create a new project called Acme"`) plus a target — either a public URL, an [environment](/director/concepts/environments) with a saved session, or a tunnel URL for local targets.
  </Step>

  <Step title="Sign in, automatically">
    If an environment is given, Director restores your saved session so it starts already signed in — no pausing to ask for a login.
  </Step>

  <Step title="The agent drives">
    Director carries out the instruction step by step while recording the session. Typed characters are never logged — only a `keyCategory` — so credentials never leak into transcripts.
  </Step>

  <Step title="Render">
    The raw recording is composited through the Screenforge render engine: automatic cursor-tracking zoom, smoothed cursor motion, captions, and fades — the same engine behind the Screenforge desktop recorder.
  </Step>

  <Step title="Verify & ship">
    Director checks whether the stated goal was actually met, then uploads the final video and returns a signed URL alongside a structured outcome.
  </Step>
</Steps>

## Get set up

The `director` CLI is how you install what Director needs and connect your agent — not something you use day to day. Run once:

```bash theme={null}
director init                # install the browser Director drives
director login                # sign in
director mcp --create-key    # connect your agent over MCP
```

Full flags and what each command does: [CLI Reference](/director/cli-reference). Need a demo to start already signed in to your product? `director session <code>` captures that separately — see [Environments & Sessions](/director/concepts/environments).

## How you'll use it

<CardGroup cols={2}>
  <Card title="MCP" icon="robot" href="/director/mcp-tools">
    The real interface — ask your connected agent to create and check on demos in plain language.
  </Card>

  <Card title="Dashboard" icon="browser">
    Manage API keys and billing, and browse the demos your agent has created.
  </Card>
</CardGroup>

## Core concepts

* **Demos** — one instruction-to-video job. Poll or wait for a structured outcome (`goalMet`, `stepsCompleted`, `whatWasShown`, `confidence`) plus a `videoUrl`.
* **Environments** — a saved target app (base URL + auth). Director can restore a captured browser session or fill a login form before recording, so the agent starts already authenticated. See [Environments & Sessions](/director/concepts/environments).
* **Structured failures** — every failure returns a `code`, a human `message`, and a `remediation` field so a calling agent can react programmatically instead of parsing English prose.

Ready to try it? Continue to the [Quickstart](/director/quickstart).