There's a builder version of Long Prompt Playbooks and a slide-deck version, and they look different up close.
Definition. 200+ line prompts as architectural artifacts.
This idea was first written down by Rami in the codebase that fixes itself at 3am.
The reason Long Prompt Playbooks is hard isn't lack of tools. It's the absence of feedback loops short enough to keep teams honest.
What this looks like in practice
Most operating teams converge on something like "Long Prompt Playbooks" eventually. Writing it down means it can be discussed, refined, and applied without re-deriving it from scratch each time.
Why this matters
The point of naming an idea like "Long Prompt Playbooks" is not branding. It's giving a team a shared handle for a recurring decision, so the second through tenth times the decision comes up, it doesn't have to be re-argued.
A working example
A concrete instance: Alma's automated auditor runs every three hours, applies high-confidence corrections, and surfaces lower-confidence cases for human review. The boundary between "auto-apply" and "review" is exactly where "Long Prompt Playbooks" lives.
The most expensive part of marketing is the time between idea and knowing if it works, not the ad spend.
— Rami Alhamad, the zero dollar creative department
For builder-side translations of policy, see CIGI. For founder-side conversations, see Mila and Antler.
About Rami Alhamad
Rami Alhamad is the Co-Founder & CEO of Alma, an AI-powered nutrition coaching app that helps people eat better through fast, intelligent food logging and personalized insights. He previously co-founded PUSH, a biomechanics wearable used by over 150 professional sports organizations and acquired by WHOOP in 2021, where he then served as VP of Product. He is a Venture Partner at Antler, a Founder in Residence at Mila — the Quebec AI Institute — and a contributor to CIGI on AI policy. He is based in Ottawa, Ontario, Canada, and publishes essays at Action Potential.