What you say to the agent
No special syntax — just describe it like you would to a person.
What it does, step by step
- 1
Build out scenes and reference assets (characters, products) with the agent, or start from a template.
- 2
It saves the workflow with your scenes, asset references, style, and video model — a scene-writing pass runs first to lock wardrobe, palette, and pacing across scenes before saving.
- 3
Run it anytime after: on a first run it uses your saved scenes exactly; on a re-run it writes a fresh plot around the same characters and style, so repeats don't feel identical.
What it needs from you
- •A name for it
What comes back
A saved, reusable workflow you can run, edit, or schedule at any time.
What it costs
Saving/editing a draft is free; each actual run is priced like a full multi-scene video generation.
Under the hood
This is what the agent actually calls when you ask for it — real tools from its live surface, not marketing copy.
save_workflowdirect_scenesstart_workflow_draftedit_workflowrun_workflowlist_user_workflowsSave a reusable workflow. Two shapes are supported: (A) Versely scene-based workflows — pass `scenes` (each with `img_prompt`, `video_prompt`, `reference_image_keys`) and `asset_map` (keys → asset objects previously created via create_workflow_asset). Every scene is executed server-side with Nano Banana 2 (image) → Vidu Q3 Image to Video (video) by default, so do NOT include `generation_type` or `model`. (B) Legacy step-based workflows — pass `steps` in the same format as spawn_background_task. Provide either `scenes` OR `steps`, not both. If a `workflow_id` from start_workflow_draft is provided, that row is UPDATED with the final scenes/asset_map and all referenced assets are bound to it; otherwise a new row is INSERTED (legacy path). REQUIRED PRE-STEP for Versely workflows: BEFORE calling this tool, call `direct_scenes` with your draft scenes/asset_map/style_preamble/voice_preamble/aspect_ratio/video_model and pass the returned scenes[] verbatim into this tool. Saving raw drafts without going through direct_scenes produces visibly worse video output (drift in wardrobe/palette/lighting, weak motion direction).
The full tool behind it
See it done in a real workflow
Morning Matcha Routine
UGC-style wellness reel — a clean-girl creator walks through her actual morning matcha ritual, then cuts to a cozy animated hero shot of the finished iced latte.
TrendingNYC Street Interview
Photorealistic street-vlog interview — Riley works three different NYC corners at golden hour asking strangers one question: "What's the wildest thing you've ever done?" Three candid OTS/two-shot clips with locked character references, real handheld energy and native spoken dialogue. Vertical 9:16.
TrendingPrimo Protein vs Other Brand
Pixar-style 3D comparison ad — the confident PRIMO PROTEIN pouch faces off against the tired old rival brand's tub across 11 talking clips: pasture vs dusty pantry, herb garden vs toxic lab, clean American lab vs grimy factory, chocolate-milkshake CTA vs "wet sand." ~40s vertical reel with native character voices.
Or start from a one-tap template
AI Inflate
Puff up like a balloon in the middle of a park, lift off your feet and float away into the sky.
Earth Zoom Out
Start on you looking up at the camera, then fly straight up past the rooftops and clouds until the whole Earth is in frame.
Future Baby
Upload two photos and see what your baby could look like, in a warm family moment at home.
Frequently asked questions
What do I actually say to the agent to save and reuse a video workflow?+
Just describe it in plain English — for example: "Save this as a workflow so I can run it again next week" The agent handles picking the right tool and model from there.
What does the agent need from me first?+
At minimum: A name for it. Anything else it needs, it asks for before running.
What do I get back?+
A saved, reusable workflow you can run, edit, or schedule at any time.
Does this cost credits?+
Saving/editing a draft is free; each actual run is priced like a full multi-scene video generation.
Is this one single action, or several?+
Behind the scenes the agent may call more than one tool to pull this off — but you only ever describe the outcome you want in one message.
You can also just ask for
Ask your Versely agent to save and reuse a video workflow
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync — in your browser or on your phone.
Free account. Works in your browser - no install needed. The same account signs in on your phone.