<aside> 🚀

🚀 FREE STRATEGY CALL

Want to grow your product through viral reach?

We help teams across iGaming, mobile apps, AI products, and SaaS build creator-led organic distribution generating tens of millions of views at CPMs starting from $0.03.

<aside> 🚀

Book a free strategy call

</aside>

On the call you'll receive:

Viral-reach gap analysis for your product
Creator-led formats already working in your niche
Estimated install / brand-lift potential at scale </aside>

A creative department is not a pile of ideas. It is twelve agents, a fixed order of operations, and a scorecard that kills weak work before a creator is ever briefed.

What is inside

Most teams run creative as a series of favours. Someone has an idea. Someone else writes a script. A creator films it. Nobody can explain why that idea beat the other nine. The output stays uneven and the learning stays at zero.

This page replaces that with a department. Twelve agents sit in a fixed order. Each one takes a named input and returns a named output. Underneath them sit the libraries the agents draw from: hooks to open with, formats to build in, brief templates to send, frameworks to judge by. Nothing here needs new software. It needs a Claude Project, a scorecard, and a decision about who approves what.

Layer	Count	Where it lives
Specialist agents	12	The twelve agents
Hooks	100	The hook library
UGC formats	50	The format library
Creator brief templates	30	The creator brief library
Testing frameworks	20	The testing library
Creative scorecard	1	The creative scorecard
Stage flow	13	The department
Feedback loop	1	The performance feedback loop

How to run any agent on this page

Two ways. Same system prompt.

Fastest, inside Claude. Open a Claude Project or a new chat, paste the agent's system prompt, then paste your inputs. You get the output straight away.
As an automation, inside Relevance AI. Create a new agent, set the model to Anthropic Claude, and paste the system prompt as the core prompt. Wire in your inputs and outputs.

Start with method one to test an agent. Move to method two once you want it running on repeat.

<aside> ⚠️

Every agent on this page produces a draft. A draft is not an approval. No creator is briefed and no asset is published until a named human has read the output, checked it against the brand rules and the claim limits, and signed it off. Agents compress the work. They do not carry the liability. Platform policy, advertising standards, disclosure rules and creator contracts stay a human responsibility at every stage.

</aside>

The department

Thirteen stages. One direction. Every stage has an owner, an input it reads, and an output the next stage can act on.

The order matters more than the tooling. Research before strategy. Strategy before ideation. Ideation before scripting. Scripting before anyone books a creator. Skip a stage and the cost reappears later as a reshoot.