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
Describe the multi-step job — anything combining several generations, like movie-plus-music, slideshow-to-reel, bulk generation, or generate-then-post.
- 2
The agent runs it asynchronously while you continue chatting, showing real-time progress rather than blocking the conversation.
- 3
Every task also saves itself as a reusable workflow, so you can ask for the same run again later without re-describing it.
What it needs from you
- •A name for the task
- •The steps to run (the agent can plan these with you)
What comes back
The finished multi-step output (video, slideshow, posts — whatever the steps produced), plus a reusable saved workflow.
What it costs
Priced as the sum of each step's generation, shown as the task plans out.
Under the hood
This is what the agent actually calls when you ask for it — real tools from its live surface, not marketing copy.
spawn_background_taskSpawn a long-running background task for multi-step workflows that take >30 seconds. The task runs asynchronously while the user continues chatting and sees real-time progress. Can be scheduled for a future time. Use for: movie creation with music, slideshow-to-reel pipelines, bulk generation, generate-then-post workflows, or any workflow combining multiple generations.
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
Frequently asked questions
What do I actually say to the agent to automate a multi-step content task?+
Just describe it in plain English — for example: "Generate 5 product images, turn them into a slideshow, and post it to Instagram — run this in the background" The agent handles picking the right tool and model from there.
What does the agent need from me first?+
At minimum: A name for the task; The steps to run (the agent can plan these with you). Anything else it needs, it asks for before running.
What do I get back?+
The finished multi-step output (video, slideshow, posts — whatever the steps produced), plus a reusable saved workflow.
Does this cost credits?+
Priced as the sum of each step's generation, shown as the task plans out.
You can also just ask for
Ask your Versely agent to automate a multi-step content task
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.