Use The Briefing Room to turn notes, transcripts, research, and fragments into a brief.
Portable judgment infrastructure
Judgment Infrastructure for Human-Led AI
Portable agent skills that help people keep context, critique, trade-offs, and evidence visible while working with AI.
Make the context legible. Challenge the thinking. Deliberate consequential choices. Create evidence before commitment.
Start Here
Use Ground Truth to pressure-test the thinking before you act on it.
Use The Quorum to deliberate trade-offs through multiple expert lenses.
Use Test Drive to turn it into the smallest credible test.
A repeatable operating flow
The Judgment Loop
You do not need the full loop every time. Start with the part that matches what you have, then carry accepted context into the next judgment move.
Ready to build? Explore the product development skills for project stewardship, product design, and frontend implementation. Use each independently or combine them as needed.
Use Cases
Use the loop for customer feedback, roadmap bets, positioning, and prioritization. Open use case.
Pressure-test pivots, senior hires, fundraising narratives, and strategic bets. Open use case.
Turn papers, interviews, notes, and evidence dumps into structured judgment. Open use case.
Clarify offers, role changes, trade-offs, and small experiments without outsourcing judgment. Open use case.
The Briefing Room
Turn messy context into a brief you can think with.
Ground Truth
Calibrated honesty and anti-sycophancy for plans, decisions, reviews, and ideas.
The Quorum
A five-member expert council that pressure-tests consequential decisions.
Applied Judgment Systems
These skills and applications bring human-led judgment into a specific kind of work.
Product development
Use any of these three skills on its own, or combine them for a coordinated build. Choose the roles your task needs.
Project stewardship
AI Project Steward
Keep decisions, approvals, and project history clear across an AI-assisted build. Check the result against what was agreed.
Explore the skillProduct & design
Product Design Director
Define the product experience, workflows, interaction design, and visual direction. Critique the rendered result.
Explore the skillFrontend engineering
Production Frontend Engineer
Implement the interface and check its behavior, visual fidelity, and technical readiness.
Explore the skillSteward also supports automations, integrations, and other technical builds. Each skill works independently; using them together does not require separate agents.
Frequently Asked Questions
What is judgment infrastructure for human-led AI?
It is a set of portable AI skills that help people structure messy information, challenge their own reasoning, and make better decisions without outsourcing human judgment.
What is an agent skill?
An agent skill is a portable set of instructions, examples, and metadata that helps an AI agent perform a specialized workflow more reliably than a one-off prompt.
What is evidence design?
Evidence design means identifying what kind of signal would make an idea more or less trustworthy, then creating the smallest useful test to gather that signal.
When should I use The Briefing Room, Ground Truth, The Quorum, or Test Drive?
Use The Briefing Room when the context is messy, Ground Truth when you want honest critique on a plan or claim, The Quorum when you need multiple expert lenses on a consequential decision, and Test Drive when you need evidence before committing.
How do I install these skills in Codex or Claude?
Install the skills you need using the linked repositories and release packages. The four core judgment skills can be installed individually or as a suite. AI Project Steward, Product Design Director, and Production Frontend Engineer each work independently; install all three if you want the combined product development workflow.