#architecture
12 posts tagged with "architecture".
-
Long-Horizon Agents: When Tasks Take Hours
• 11 min readSix-hour agent runs are now real. The harness — checkpoints, durable state, recovery — matters more than the model. A field guide to the long-running pattern.
-
Skills, Connectors, Subagents: Anthropic's 3-Layer Agent Template
• 10 min readAnthropic just shipped 10 financial services agent templates. The interesting part isn't the templates — it's the three-layer architecture quietly becoming the standard for enterprise agents.
-
Cascaded vs Fused Voice Agents: A Builder's Perspective on Architecture Choices
• 16 min readDeep dive into voice agent architectures. Why cascaded models give you control and fused models trade complexity for naturalness. What we're learning from shipping production agents at scale.
-
Cost-Optimized Agent Architectures: Cutting Spend 10x Without Losing Quality
• 9 min readCaching, routing, distillation, and per-task model selection. The four moves that take a $0.40/task agent to $0.04/task without anyone noticing the difference.
-
Deep Agents: Planner / Executor / Critic Becomes the Default
• 10 min readThe three-role pattern that powered Manus, then LangChain Deep Agents, then half the production agents shipping in early 2026. Why it works, when it doesn't, and how to actually build one.
-
Agent Memory Architectures: Short-Term, Long-Term, and Episodic
• 9 min readThree kinds of memory, four-tier consolidation pipelines, hybrid retrieval that beat pure vector search, and the unsolved staleness problem. The 2026 state of the art for agents that learn over time.
-
Google ADK: An Architectural Tour of the Agent Development Kit
• 9 min readGoogle's Agent Development Kit isn't another agent loop. It's an event-driven runtime, a multi-language SDK, and a deploy target that lines up with Cloud Run and GKE. Here's how the pieces fit.
-
Sub-Agents Are the New Microservices
• 9 min readThe orchestrator-worker pattern that took over agent design in late 2025 is the same pattern that took over backend design in 2014. The wins are real. So are the failure modes.
-
Choosing an Agent Framework in 2026: A Decision Tree
• 9 min readSix serious frameworks, four orchestration styles, and one tired question I keep getting asked. Here's the decision tree I actually use.
-
LangGraph Deep Dive: State Machines for Multi-Step Agent Workflows
• 8 min readLangGraph turns the agent loop into an explicit state graph — nodes, edges, reducers, checkpointers. The mental model, the type system, and the patterns that make it production-grade.
-
LangChain in Production: Composability and the Parts That Survived
• 7 min readLangChain is no longer the agent framework — LangGraph is. But its primitives (runnables, retrievers, callbacks) became the connective tissue underneath. Here's what to keep and what to drop in 2026.
-
Anatomy of an AI Agent: From Prompt Loops to Production Systems
• 9 min readWhat actually goes inside a production AI agent — the reasoning loop, the tool layer, memory, control flow, and the surface where models meet your business systems.