Framework
The Intelligent Product Engine
A three-part architecture that makes AI generation predictable and enterprise-appropriate: context archetypes (different rule sets for different modes), real-time artifact monitoring (Figma and git sync to structured artifacts for humans and AI), and a rules engine (WCAG, brand governance, legal gates, release criteria). Each part is necessary; together they turn generative AI from a prototype toy into a production tool.
How it works
- 1Context archetypes: named configurations that define how the system behaves in a specific mode — creative exploration vs. compliance review produce reliably different outputs from the same underlying model.
- 2Real-time artifact monitoring: Figma files and git repos are continuously parsed into structured data that both humans and AI can consume, keeping the design system current rather than snapshot-based.
- 3Rules engine: encodes WCAG accessibility standards, brand governance, legal requirements, and release gates — so constraints are applied automatically at generation time rather than in a post-hoc review.
- 4The three parts work together: archetypes set the mode, artifacts provide the material, rules define the boundaries. Remove any one and AI generation becomes unpredictable.
- 5This is what separates a design system tool from a design system platform: a tool stores components; a platform enforces rules and generates compliant artifacts on demand.
Hear it on the podcast
Stop Designing Screens, Start Designing PatternsListen to the episodeMore from this episode
Prototype and PruneAI is a proxy for skill, not taste. Generate multiple enterprise-appropriate prototypes using real design system context, then let a human with taste prune down to the right one. Coined by Jules at Meta, reinforced by Scott Belsky. The bottleneck moves from production to curation — and curation is the irreducible human job.Design Systems ThinkingStop designing individual screens. Start designing systems of experiences. Every interface element is a pattern with explicit rules and constraints — not a one-off creative decision. This shift from instance-level to system-level abstraction is what enables consistent product experiences at scale and makes AI generation enterprise-appropriate.
Get the next framework first
One email a week with the frameworks, tools, and founder stories from the podcast. Free.
More frameworks for AI & Automation
The Collaborative Results IndexMeasure human-AI collaboration on three axes — not just usage. Results: what's the actual impact? Relationship quality: are humans genuinely engaging as collaborators, asking good questions, thinking critically? Resilience: is the human developing domain expertise through the collaboration, or outsourcing judgment and atrophying? The third dimension is the dangerous one: the cognitive muscle you don't train, you lose.Process Redesign vs. Process AutomationDon't automate your existing workflow. Ask what process you'd design from scratch if you could do things that weren't previously possible. The difference isn't speed — it's architecture. Existing processes are designed around human cognitive limits (six to seven post-it notes, six to seven ideas). AI-native processes blow past those constraints: 300 customer needs, 400 product ideas, synthetic testing across all of them, human judgment reserved for the handful that survive filtering.Metacognitive AI CollaborationThinking deliberately about how you're thinking — what to keep in your brain vs. what to outsource to AI, and what questions are worth asking when you can get an answer to any question in two seconds. The foundational AI collaboration skill. Prompting can be trained in an afternoon; metacognition is what separates people who get better through AI from people who get worse.The AI Factory EffectAI compresses delivery timelines — but scope expands to fill the gap. Teams don't get time back; they ship more. MVPs complete faster and then continue straight into features, architecture, and workflow automation. Same headcount. Same contract length. Dramatically more output. The promise was leverage. The reality is a factory. Plan your workload, pricing, and client expectations around this dynamic, not the old assumptions.Trust Before AutonomyAI agents are trust-limited, not capability-limited. They can already do more than most organizations are comfortable delegating. The unlock isn't a better model — it's accumulated evidence of reliability. Trust is built through transparency (sources, confidence levels, disclosure), demonstrated consistency over time, and gradual expansion of autonomous scope as each new boundary proves safe. Autonomy follows trust; it does not precede it.The Four-Category AI Coding TaxonomyAI coding tools fall into four distinct categories with different users, capabilities, and failure modes: (1) generalist code assistants (Copilot, Cursor) for developers; (2) prototyping tools (Lovable, Bolt, v0) for fast front-end visualization; (3) lifecycle agentic flows (Devin) for engineering teams across the full SDLC; (4) MVP builders (Lio) for full-stack requirements-to-scaffold generation. Knowing which category you're in tells you what to expect, where you'll hit walls, and where to go next.