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
Point the agent at a saved workflow that already has scenes and reference assets set up.
- 2
Tell it your cadence in plain English ("every day at 10am", "3 times a week") — it converts that into a schedule itself.
- 3
On each run, it writes a fresh plot/script while reusing the same characters, style, and assets, generates the full video, and — if you asked for it — auto-posts the result to your connected accounts with a written caption.
What it needs from you
- •Which saved workflow
What comes back
A recurring series that generates a new, on-theme video on your schedule, optionally auto-posted.
What it costs
Each run is priced like a full video-workflow generation, charged when that run actually generates — not when you set up the schedule.
Under the hood
This is what the agent actually calls when you ask for it — real tools from its live surface, not marketing copy.
schedule_workflowset_workflow_modeTurn a saved Versely scene workflow into a recurring series: on each scheduled tick, Gemini writes a fresh plot/script (new scenes with new prompts) while reusing the same asset_map (characters/products) and style_preamble, then generates the video end-to-end. Optionally auto-posts the final video to connected social accounts with an LLM-written caption. Use this whenever the user asks to 'schedule', 'run every day / N days / certain weekdays', 'make a daily series', 'post automatically', etc. To stop a schedule, call this with active=false. IMPORTANT: you must translate the user's natural-language cadence into a standard 5-field UTC cron expression yourself — e.g. 'every day at 10am' → '0 10 * * *', 'Mon/Wed/Fri' → '0 10 * * 1,3,5', 'every 2 days' → '0 10 */2 * *', '3 times a week' → '0 10 * * 1,3,5'. Ask the user their preferred local time if unclear; accept it as UTC if not specified. Before scheduling, make sure the workflow already has a scenes array and asset_map saved (via save_workflow). Prefer set_workflow_mode when the user uses the words 'auto' or 'manual'.
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 run a recurring video series?+
Just describe it in plain English — for example: "Turn this workflow into a daily series that posts to TikTok every morning" The agent handles picking the right tool and model from there.
What does the agent need from me first?+
At minimum: Which saved workflow. Anything else it needs, it asks for before running.
What do I get back?+
A recurring series that generates a new, on-theme video on your schedule, optionally auto-posted.
Does this cost credits?+
Each run is priced like a full video-workflow generation, charged when that run actually generates — not when you set up the schedule.
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 run a recurring video series
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.