Free. No email gate.
AI marketing prompts, with the reasoning included.
107 prompts, written carefully and shared openly — each one includes the variables it expects, where it tends to break, and how it's changed over time.
How the four-stage pipeline works
0
prompts
0
departments
0
tiers
Marketing OS
● live107 prompts across 36 departments, covering most of what a marketing team does.
Enter the OS
Product OS
coming soonPRDs, discovery, roadmaps, launch. Same engineering standard.
Featured departments
All 36 →Content Engine
The four-stage content pipeline: Classifier → Strategist → Writer → Editor.
4 prompts
Dept 09Meta / Operations
The prompts that manage the prompt system itself — QA, post-mortems, routing.
3 prompts
Dept 03AI Visibility (AEO/GEO)
Getting your brand cited when AI assistants answer the question.
2 prompts
Built on seven principles
01
Contracts everywhere
Every prompt declares inputs and a machine-parseable output, so any prompt's output can feed another prompt. That's what makes 107 prompts an operating system instead of a pile.
02
Honesty valves
Prompts are allowed to return INSUFFICIENT_DATA, REJECT, or "don't run this campaign" instead of forcing an output. Nobody reviews every output before it ships, so the prompt has to be its own skeptic.
03
Evidence binding
No invented stats, quotes, cultural claims, or persona traits; everything cites its input or gets flagged [NEEDS SOURCE] / [NEEDS NATIVE REVIEW] / [LEGAL REVIEW].
How to use a prompt
01
Fill in the variables
Each prompt has a form for its variables — type in your specifics and watch them fill in as you go.
02
Copy it
Copy the raw prompt, or copy it with your values already filled in.
03
Run it
Paste it into whichever AI model the prompt is written for, and use what comes back.