👉 Quick Start

Why Use This Playbook?

Designing for AI introduces conflicting assumptions, jargon, and mental models. This playbook gives teams a shared vocabulary and a step-by-step way to make clear, testable decisions fast.

When to Use This Playbook?

  • Exploring a new AI feature or product to frame options clearly.

  • Aligning a cross-functional team to establish shared vocabulary and decision flow.

  • Auditing an existing AI experience to check for gaps in trust, control, and UX.

What is a Play?

A Play is a structured recipe for designing an AI feature or system across the following building blocks.

  • 🎛️ Interaction Models - How users engage with the AI.

  • 🔌 Integration Models - Where AI fits in your product ecosystem.

  • 🧱 Archetypes - Which components (agents, tools, workflows) are in play.

  • 💠 Dimensions - How capabilities and properties (autonomy, context, scope) are defined.

  • ⚙️ Runtime Behaviors - How AI behaves when operating.

  • 👨‍💻 Human Roles - Who configures, monitors, and interacts with the system.

  • 📃 System Prompts - How the system is instructed to behave.

  • 🎯 Evaluations - How the system is measured and controlled.

  • 📐 Design Considerations – Patterns for trust, transparency, and control.

How to Use This Playbook?

  • Compose a Play by selecting elements from each section.

  • Apply Design Considerations to ensure trustworthy, user-centric experiences.

  • Use the Play Template as your checklist

Updated on