Architectural Patterns
Patterns are reusable architectural designs and structural solutions to common problems. They describe the topology and relationships between agents and systems. Think of this as the “Engineering” of the domain.
What belongs here:
- Architectural topologies (e.g., “Supervisor Agent”, “Context Gates”).
- Common interaction models between components.
- Solutions to recurring design challenges.
- Structural diagrams and flow descriptions.
Ralph Loop
LivePersistence pattern enabling autonomous agent iteration until external verification passes, treating failure as feedback rather than termination.
Agent Constitution
LivePersistent, high-level directives that shape agent behavior and decision-making before action.
Adversarial Code Review
LiveConsensus verification pattern using a secondary Critic Agent to review Builder Agent output against the Spec.
Constitutional Review
LiveVerification pattern that validates implementation against both functional requirements (Spec) and architectural values (Constitution).
Model Routing
LiveStrategic assignment of LLM models to SDLC phases based on reasoning capability versus execution speed.
The ADR
LiveA structural pattern for capturing architectural decisions with context, rationale, and consequences in an immutable record.
Experience Modeling
LiveThe practice of treating the Design System as a formal schema that agents must strictly follow, preventing UI hallucinations.
Product Vision
LiveA structured vision document that transmits product taste and point-of-view to agents, preventing convergence toward generic outputs.
The PBI
LiveA transient execution unit that defines the delta (change) while pointing to permanent context (The Spec), optimized for agent consumption.
Specs
LiveLiving documents that serve as the permanent source of truth for features, solving the context amnesia problem in agentic development.
Agentic Double Diamond
ExperimentalA computational framework transforming the classic design thinking model into an executable pipeline of context verification and assembly.
Agent Optimization Loop
ExperimentalThe recursive process of using feedback from scenarios to continuously tune agent prompts, context, and tools.
Context Map
ExperimentalA high-density navigational index that enables agents to locate knowledge without managing massive context windows.
Spec Reversing
ExperimentalUsing frontier models to derive specifications from existing code to bootstrap the Agentic SDLC in brownfield projects.
Context Gates
ExperimentalArchitectural checkpoints that filter input context and validate output artifacts between phases of work to prevent cognitive overload and ensure system integrity.
External Attention
DraftExternal Attention offloads document processing to isolated sub-agents, returning only extracted answers to the main agent's context window.