How to edit video with ChatGPT Work or Claude Cowork

What you need

• Cadre on macOS 13 or later, with a project you've recorded.
• The ChatGPT or Claude desktop app on the same Mac.
• Your own assistant account; Cadre includes no AI credits or model usage.

That's it. Cadre's editor is fully data-driven — a project is a manifest plus timeline data — so the app can expose the whole edit as tools an agent calls. You describe the outcome; the agent chooses the tools and verifies each change.

1. Record your demo

Open Cadre and record as normal: your screen with system audio, mic and webcam, or an iPhone/iPad mirrored over USB. As you record, Cadre tracks every click, scroll and cursor movement, and never what you type. That interaction data is what makes the next part possible — the agent (and Cadre's own auto-zoom) can see where the action was, not just the pixels.

Most people will press Record themselves because they know what they want to show. A connected agent can also call start_recording, but Cadre creates the same floating recording controls as a human start. The countdown defaults on but can be disabled; for screen and area capture, the target highlight and other-display dimming are conditional, best-effort cues. macOS permissions still govern desktop capture.

2. Write the brief and open the request

Open Edit with AI, select the recording, and describe the result in What would you like to change?. The brief remains editable until you choose a destination. Cadre includes the selected project ID so the assistant can verify it before changing anything.

● ChatGPT Work — Connect & open
● Claude Cowork — Set up Cowork
● Draft opens for your review

For ChatGPT Work, choose Connect & open. Cadre installs its local plugin and opens the prepared ChatGPT draft. For Claude Cowork, choose Set up Cowork, upload the generated ZIP once in Claude's Customize → Plugins screen, enable Cadre, then choose Open in Cowork. The Cowork plugin contains both editing and motion graphics skills and needs no Node.js installation or terminal command.

Cadre registers its 62 tools for either assistant path and keeps the private local connection current across app restarts.

Review the draft and press Send yourself. Keep Cadre and the assistant desktop app open on the same Mac while editing; a cloud-only chat cannot reach Cadre's local service. Claude Code, Codex and compatible MCP clients remain available as secondary setup paths in the agent docs.

3. Direct the edit

Now describe what you want the way you'd brief an editor. Under the hood the agent selects from Cadre's v1 tools — here's how a few common requests map to real calls:

• It reads the current state with get_timeline (durations, zooms, cuts, speeds, captions).
• It removes dead air with add_cut and ramps slow stretches with set_speed.
• It places cinematic zooms with add_zoom — Cadre's spring physics handles the push-in and ease-out.
• It starts on-device transcription with generate_captions, polls the owned job to completion, and styles the result with set_style.
• It renders with export_video and polls get_export_status until the MP4 is ready.

Every tool validates its arguments and returns a verifiable result; long local work uses a bounded job receipt and explicit polling. The agent can confirm each change landed the way you asked — and undo it with undo if you don't like it.

Prompts that actually work

You don't call tools; you describe outcomes. These map cleanly onto the v1 surface:

What a full session looks like

One prompt can carry the whole edit. Here's the shape of it — you say one sentence, the agent reports back what it did:

# you just finished recording a 4-minute product demo
› open my latest project, tighten it, zoom the terminal
  on every click, caption it, and export at 1080p

# the agent works through the tools and reports back
● open_project      loaded "api-walkthrough"
● get_timeline      4:12 · 0 zooms · 0 cuts
● add_cut           trimmed 3 silent gaps  −0:47
● set_speed         2× ramp over a 22s idle stretch
● add_zoom          6 zoom keyframes on terminal clicks
● generate_captions 38 segments · on-device
● export_video      rendering… get_export_status 100%
✓ demo.mp4  1080p · H.264 · 3:25

Your assistant handled the first pass; you then review the timeline and finished preview before export. If you want to see exactly which tools exist and what each returns, the tool reference lists the full v1 set.

When to still edit by hand

Agent editing isn't all-or-nothing. The agent is great at the mechanical passes — cutting dead air, placing zooms on activity, captioning, exporting. But taste is yours. Open Cadre's editor directly when you want to:

• Nudge a single zoom's framing or timing to land a beat exactly right.
• Fine-tune the background, device frame or webcam position for a specific shot.
• Scrub and preview before committing to an export.

A good flow starts with a clear brief and ends with a human review. Let your assistant handle the first pass, then polish the moments that carry the demo. Everything the assistant does is a normal, reversible edit on the same timeline you'd touch by hand.

FAQ