
Test ten angles, not one guess.
Feed the pipeline a list of hooks and angles, loop over them, and let per-step caching do the math: ten variants cost a rerun, not a production cycle, and every one stays recognizably on brand.
One can. Ten angles.
Every angle is a line in a list. The workflow loops over it and the brand holds in each one.
- Hooks list
- Brand voice
- Script
- Video
- Captions

Story · 9:16
Post · 4:5
Banner · 16:9Done. Change the input and run it again.
Why it holds up
Ten variants per rerun
The hook list is an input. The pipeline loops over it, and only the steps a new hook touches recompute; everything else stays cached.
On brand at any volume
The brand kit's voice and look steer every script and caption, so variant thirty is as recognizably yours as variant one.
Ship the winner as an app
When a variant wins, publish its pipeline as a simple form. The team types a hook and presses run, no canvas required.
Build it once. Run it again.
The workflow behind this page, step by step. Every step is a node you can open, change and rerun.
- 1Hooks
Write the list, not the ads.
Ten hooks, ten angles, one text node. The pipeline loops over the list and builds a variant for each entry.
Add an eleventh next week and rerun; only that variant's steps compute, the other ten stay cached.

- Hook 01
- “The tote that survived three festivals”
- Hook 07
- “Why our returns rate embarrasses us”
- Loop
- 10 entries → 10 variants
- 2Script + video
Every angle, same voice.
The brand kit steers each script, then a video model turns it into the spot. Swap veo-3 for kling-3 without rewiring the graph.
The canvas shows the estimated credit cost of the full loop before you press run, so a big test is never a surprise.
FlowHooks × loop → script → veo-3 → captions
- 3Ship
Promote the winner, keep the pipeline.
When results come back, the winning variant's pipeline is already built. Publish it to the team as an app, or trigger batches through the public API.
Pause any step for human review, so nothing ships that a person didn't sign off on.
This week's hooks12 hooks · 12 variants queued
Run
What you can make.
Starting points for dtc creative testing. Each one is a workflow you can open, change and run again.
- 01
Hook test batches
Ten opening lines on one product, each built into a full video variant.
- 02
Angle matrices
Problem, proof, offer and founder-story angles side by side for the same SKU.
- 03
UGC-style hooks
An AI actor reading each hook, cut for paid social.
- 04
Static iterations
Image variants that change one thing at a time: the headline, the background or the crop.
- 05
Offer refreshes
Swap the offer line for a sale weekend and rerun only the steps it touches.
- 06
Briefs into workflows
Describe the test you want and the copilot drafts the workflow behind it.

Every variant, one rerun.
Open a template, paste your URL for the brand kit, and loop your first hook list on the free tier. Costs show on the canvas before every run.
With the rest of Orisu.
The workflow is one part. These are the other parts teams use with it.
Brain →Brain keeps your claims, tone and words to avoid, so variant thirty sounds like variant one.
Feed →Take the winning angle across every product in the catalog, one row per SKU.
App Mode →Give the growth team a form with a hook field and a run button.
API and MCP →Trigger the same workflow from your own code, or from Claude and ChatGPT, and get the files back.
Good to know.
How many variants can one run make?
As many as there are items in your list. The pipeline loops over them, and the estimate shows the total cost before you press Run.
Can someone approve variants before they're used?
Yes. Add a Human review step and the run pauses until a person picks the items that continue. Only approved items move on.
Can I test across the whole catalog?
Yes. Put the workflow in Feed as a column and every product row gets its own variants.
What is creative testing at scale?
Running many ad variants, each with a different hook, angle or opening, against each other to find what converts instead of betting on one concept. Orisu makes it a loop: the pipeline iterates over your hook list and builds a variant per entry, with per-step caching so only changed steps recompute.
How do I test different hooks without redoing the whole ad?
The hook is an input, not part of the build. Change the list and rerun: steps that didn't change are cached, so a new hook only recomputes the script, video and captions it actually touches.
How do AI ad variants stay on brand?
Paste your site URL once and Orisu builds a brand kit: colors, fonts, voice and logo. Every script and caption node reads from it, so thirty variants share one personality instead of drifting into thirty.
Do I have to build this workflow myself?
No. Start from a template, or describe what you want and Orisu drafts the workflow for you. You can also build it step by step.
What does it cost to run?
Every node shows its credit cost on the canvas, and a run shows its total before you press it. The free plan gives you 100 credits a month with no credit card.
Can my team use it without learning the canvas?
Yes. App Mode turns the workflow into a simple form: inputs on top, a run button, results below.
Can I change models later?
Yes. Models sit behind the same ports, so you can swap one without rewiring anything. All of them are on one subscription.
Test more, guess less.
Start free: paste your URL for the brand kit, load a hook list, and run your first test loop today.