Skip to main content
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

1

Brief

You send an instruction ("Sign in and create a new project called Acme") plus a target — either a public URL, an environment with a saved session, or a tunnel URL for local targets.
2

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.
3

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.
4

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.
5

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.

​
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:
Full flags and what each command does: CLI Reference. Need a demo to start already signed in to your product? director session <code> captures that separately — see Environments & Sessions.

​
How you’ll use it

MCP

The real interface — ask your connected agent to create and check on demos in plain language.

Dashboard

Manage API keys and billing, and browse the demos your agent has created.

​
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.
  • 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.