Pattern Catalog

What problem are you solving?

Find the question below that matches your current concern and jump to the pattern.

Is this responsibility independent enough to live in its own agent?

Responsibility Partitioning

Under what conditions must this module refuse or fail?

Module Contract

What must this agent not be unaware of right now?

Context Routing

What stays in the session, and what gets promoted to system memory?

State and Memory Control

By what criteria do we measure quality and risk?

Evaluation and Guardrails

When should the agent stop and hand off to a human?

Human Approval

Does this reasoning step really need this model?

Cost Control

Can the rationale of this agent's decision be explained after the fact?

Decision Traceability

Pattern Relationship Map

The eight patterns are not independent. Responsibility and ownership determine the collaboration structure, and the collaboration structure produces the demands of trust and verification. Patterns connected in the map below have outsized effect when applied together.

Pattern placement and connections by category

Relationship to implementation patterns

The governance patterns of reopt architecture are complementary to Google's multi-agent implementation patterns and others. Governance patterns answer "what must be honored;" implementation patterns answer "how to build."

Governance pattern	Implementation pattern	How they connect
Responsibility Partitioning	Hierarchical Decomposition Parallel Fan-out/Gather	A parent agent decomposes the goal into sub-responsibilities and delegates them. Parallelizable responsibilities are realized as Fan-out; sequentially dependent ones as Hierarchical.
Module Contract	Spec-Driven Development	The contract's input/output schema becomes an executable spec that generates code, docs, and mocks. An MCP Tool Definition is one concrete realization of a module contract.
Context Routing	Sequential Pipeline Routing Pattern	At each pipeline step, rules filter and structure the context passed to the next agent. The Routing Pattern branches inquiries to the appropriate agent based on type.
State and Memory Control	Session Store / Vector Memory	Mostly an infrastructure-design concern. Key implementation work: separating session store (short term) from vector DB / knowledge base (long term) and controlling read/write authority.
Evaluation and Guardrails	Generator-Critic Evaluator-Optimizer	A reviewer agent evaluates the generator agent's output. Up-front guardrails block before execution; post-hoc evaluation is realized through the Generator-Critic loop.
Human Approval	Human-in-the-Loop	Asynchronous approval queues and approve/deny callbacks are the core implementation elements. The default is an asynchronous structure that lets other work continue while approval is pending.
Cost Control	Token Budget Management Model Routing	Combines route-based model selection (high risk = strong model, low risk = lightweight), per-agent token budgets, and caching/batching strategies to control the cost curve.
Decision Traceability	Structured Logging Distributed Tracing	Collects per-agent decision logs in structured form (JSON, OpenTelemetry spans) and implements tracing infrastructure that captures causal relationships.

Responsibility & Ownership

Responsibility PartitioningName the owner of each outcome and draw the boundary around it.
Module ContractDeclare the conditions, authority, and failure paths of every execution unit.

Collaboration & Coordination

Context RoutingDesign information flow so each participant receives exactly what it needs.
State and Memory ControlSeparate short-term state from long-term memory to prevent leakage and confusion.
Cost ControlManage token budget, model selection, and call frequency structurally to control the cost curve.

Trust & Verification

Evaluation and GuardrailsDistinguish acceptable judgment from dangerous judgment via evaluation criteria and safety rules.
Human ApprovalKeep high-cost, high-risk, high-impact decisions inside a human-approval flow.
Decision TraceabilityRecord judgment rationale, choices, and collaboration paths as structured logs.