Design Language for the Post-App Era
Human life is not a task queue. The same AI action can be helpful, rude, or dignity-preserving depending on the moment. Context Grammar asks what AI needs to understand about a human situation before it earns the right to act.
Context Grammar Flow: How intent becomes action
A real person in a real moment — with history, context, and a goal.
Explicit or inferred. Not a text string — a structured goal object.
6 context signals + 2 trust dials — describing where you are and what the system can do.
Three layers: Identity (months), Learning (weeks), Now (seconds). Five Brain types.
Tokens × Brain → design rules → 23 AX Patterns. Delegate, escalate, or adapt.
A five-floor pipeline from Intent to AX Patterns, plus Trust Design and Specs. Read in any order — each stands alone.
Four channels of human signal — explicit, active, passive, ambient. Intent is a structured goal, not a text string.
ReadSix situation signals and two trust dials — the variables that describe where you are and what the system can responsibly do.
ReadThree layers of memory — Identity, Accumulated Learning, Right Now. Five Brain types for a home. Every Brain has the same anatomy.
ReadAutonomy Dial: how much the system acts without asking. Disclosure Dial: how much personal context you share. Per-domain. User-owned.
ReadTokens × Brain → design rules. Resolves collisions when Priority Weight conflicts arise. Three exits: Delegate, Escalate, Adapt.
Read23 named patterns — Delivery, Escalation, Autonomy, Cross-cutting — describing how UI should behave when the Rule Engine fires.
ReadYAML schema definitions for Context Tokens, Brain layers, and AX Pattern triggers — making the framework portable across teams and platforms.
ReadMemory is the hardest part of agentic design to get right. The three-layer structure is the foundation everything else builds on.