I reuse the architecture components behind my production AI systems: agents, memory, orchestration, retrieval, and tools, for engineers and technical buyers.
The architecture patterns I reuse across projects.
Coordination, state transitions, and typed execution boundaries for agents that need to work together.
Episodic memory, semantic retrieval, compression, and replayable context for agents that need continuity.
Durable execution, retries, branching, checkpoints, and human gates for AI workflows in production.
Embedding pipelines, hybrid search, metadata filters, reranking, and stable eval sets for RAG systems.
MCP integrations, typed tools, permission boundaries, routing schemas, and protocol adapters.
Regression suites, adversarial cases, trace review, cost tracking, and evidence that a system is ready to ship.
One hub per topic: each connects the concept to its components, projects, and articles.
Architecture patterns for coordinating multiple AI agents with clear roles, shared state, tools, and failure handling.
Routing, delegation, checkpoints, and supervision patterns for agent workflows in production.
Durable workflow design for AI systems that need branching, retries, persistence, and audit trails.
Patterns for AI workflows that survive partial failure and remain inspectable after each run.
Memory layers for AI systems: semantic recall, episodic traces, compression, persistence, and retrieval evaluation.
Model Context Protocol integrations, connector identity, tool boundaries, and operational interfaces for agents.
Hybrid search, embedding pipelines, metadata strategy, reranking, and evals for RAG systems in production.
Tell me about the operational problem you want to solve. A few lines about the context and the systems involved are enough for a first assessment.