The AI panel is where you describe a task, give ChatCut precise project context, approve generation, and follow the agent’s work. It normally appears on the left side of the editor.
How do I open the AI panel?
If the panel is hidden, open the Workspace menu in the top bar and enable AI. Choose Reset to default from the same menu if several panels have moved or disappeared.
The panel has three main regions:
- Conversation: your requests, agent replies, progress, questions, and generation confirmations.
- Prompt composer: the field at the bottom where you enter the next task and add context.
- Composer controls: the mode, settings, attachments, reusable context, Selection Mode, and Send or Stop button.
Start from a workflow card
In a new or empty AI conversation, ChatCut can show workflow cards above the Prompt composer. Select a card to insert its starter Prompt, review or change the proposed inputs, and then send it. Selecting a card does not start the task by itself.
| Card | What it prepares |
|---|---|
| Talking Head Editing | A speech-led edit covering take selection, filler and pause cleanup, pacing, B-roll, captions, motion graphics, and music. |
| Motion Graphics | A motion-graphics brief based on the message, content, brand cues, and optional image references. |
| Seedance 2.5 | A guided AI-video request covering the subject, action, scene, mood, duration, aspect ratio, and useful image, video, or audio references. The card also selects Seedance 2.5 for the draft. |
| Product / App Promo | A product promo that can start from a URL or from uploaded product images, logos, screenshots, and key details. |
| AI Short Film | A short-film workflow covering the creative brief, story structure, style bible, shot list, prompts, continuity, generation, and final edit. |
| Explainer Video | A topic-and-duration brief that can combine narration, stock footage, motion graphics, generated clips, and music. |
| Collage B-roll | Animated paper-collage B-roll built around one spoken line or abstract concept, with a visual metaphor and still/animation approvals. |
| Voice Cloning | A voiceover workflow that checks for an existing custom voice or guides you through cloning one, then collects the script, language, tone, and Timeline placement. |
Some cards display a required feature or plan badge. If a card is unavailable, use the visible plan prompt to check access. You can also ignore the cards and type a normal request directly into the composer.
What is below the Prompt field?
From left to right, the available controls can include:
- Agent / Video Gen: switches the workflow used by the composer.
- Agent settings: the sliders button beside Agent mode.
- Upload (+): attaches files to the current AI draft.
- Video generation model, Voices, Design Styles, and Skills: attaches reusable generation or workflow context to the current draft.
- Selection Mode: turns editor selections into precise
@references. - Send message / Stop: sends the draft or asks the current task to stop.
Some controls appear only in the mode or product surface that supports them. Attaching a Skill, style, voice, or model changes the current draft; it does not start generation until you also describe the task and send it.
What changes between Agent and Video Gen?
Agent keeps the conversation and project-editing workflow. Use it when ChatCut should inspect project context, perform several operations, or revise the timeline.
Video Gen replaces the Agent composer with direct video-generation controls. You choose the model, input mode, references, and output settings before sending one generation job. Switching modes does not change the active timeline, but incompatible draft inputs may be removed or replaced.
Where do results appear?
Agent progress and questions appear in the conversation. Imported and generated media appears in My Assets. Timeline edits appear in the active Timeline and can be reviewed in the Viewer. A task can therefore finish with a new asset, a changed timeline, a response in the conversation, or a combination of all three.
Continue to Prompt Composer for sending context, Selection Mode for precise references, or View Task Progress and Results for monitoring work.