revenue design system
MESSAGE.md is a dynamic messaging specification for agents built to keep AI-generated content consistent, relevant, and uniquely yours - without breaking the token bank.
Check the specthe messaging house
codified positioning and messaging that defines the brand, the audience, and the portfolio - with the proof to back it up
Structured documents for what every asset type looks like for you, with the conventions to design and produce.
Granular profiles loaded on demand for specific personas, products, competitors, segments, and more.
Foundational messaging documents — the company, narrative, market, audience, and portfolio, with the proof to back it all up.
Company facts, glossary of terms, brand guardrails, and scenario dimensions. Agents load this first, always-on.
the messaging room
the right message, at the right time, for the right reasons
MESSAGE.md loads first — attributes, glossary, guardrails, and the scenario vocabulary. Always on.
The agent reads the task and combines the four dimensions into the scenario at hand.
Only the pillars, collections, and assets whose Load When conditions match get pulled in.
The result is tightly scoped context assembled per task — not the entire messaging house in every prompt. Message optimized, token optimized.
the messaging room
the right message, at the right time, for the right reasons
The result is tightly scoped context assembled per task — not the entire messaging house in every prompt. Message optimized, token optimized.
the content factory
one scenario in, a full set of on-message assets out
Infer dimensions from user/agent input.
Load the relevant messaging context.
Work through guided session to lock POV.
Determine key messages and asset selections.
Subagents spawn to write from the plan.
Plug into templates or pass to design tools.
why it holds up
Drop MESSAGE.md and the messaging/ directory into any repository. Your AGENTS.md or CLAUDE.md teaches the agent how to read and use it.
Assembly is driven by the scenario, so the agent delivers the right message at the right time for the right reasons.
Tight, per-task context assembly avoids confusion, hallucination, and bloat.
LLMs already know how to write. What they need is structured output and company-specific rules for better content and downstream production.
Market moves, competitive shifts, and new innovations land as reviewable file changes — the house stays maintainable by agents.