Blog
Writing
Life, tech, and everything in-between.
Choosing the Right Agentic Pattern: A Decision Framework
Thirty-three articles into this series, the question becomes how to pick among the patterns rather than how to build any one of them. A small set of decision trees and a simplicity test cover most cases.
MCP and A2A: Protocol Standards for LLM Agents
For a decade, every tool integration and every inter-agent communication was bespoke. MCP standardizes the data side: any client connects to any tool server. A2A standardizes the agent side: agents discover and call each other across organizations.
Scaling and Cost Optimization for LLM Agentic Systems
Multi-agent architectures amplify both capability and error. Google DeepMind measured the amplification across 180 configurations. Anthropic reports 90 percent cost reductions from a planner-plus-workers split. Both results inform how to scale production agents.
Harness Design: Planner, Generator, Evaluator for Production LLM Agents
A harness is the set of components around a language model that turn a research prototype into a production system. Anthropic's three-agent architecture (planner, generator, evaluator) mirrors the GAN discriminator-generator dynamic and survives long-running applications.
Agent Evaluation: LLM-as-Judge, Pass-at-K, and Benchmarks
An agent that cannot be measured cannot be improved. Evaluation starts with twenty queries and an LLM-as-judge, scales up through pass-at-k metrics and standard benchmarks, and never trusts any single layer alone.
One Word, Three Jobs: What "Agent" Means at Lunch and in Production
The lunch-table conversation about AI agents and the production-engineering conversation about AI agents are both right. They are talking about three different things and calling all of them "agent."
Guardrails for LLM Agentic Systems: Layered Defense
Safety instructions in a system prompt are not sufficient for production. Benchmark agents still behave unsafely in a significant fraction of cases. The fix is layered defense: prompt-level, tool-level, model-level, and system-level guardrails stacked so any one failure is caught by the next.
Human-in-the-Loop Patterns for LLM Agents
Full autonomy is not the right target for every agent. Put a human in the loop at the points that matter: before dangerous actions, for ambiguous decisions, as an escalation path when the agent is stuck. Checkpointing makes the pauses cheap.
Skills as Contextual Memory: Reusable Procedural Knowledge for LLM Agents
Anthropic's Skills pattern packages reusable procedural knowledge as folders of instructions, scripts, and resources. Progressive disclosure loads only the metadata at startup and brings in the details on demand. Context capacity becomes effectively unbounded.
Persistence and Checkpointing: Time Travel and Recovery for LLM Agents
A long-running agent that loses its state on the next deploy is not a production system. Checkpointing saves agent state after every step, enabling conversational memory, human-in-the-loop pauses, time travel for debugging, and fault-tolerant resumption.
Generative Agents Memory: The Stanford Architecture for Persistent LLM Agents
Stanford's Smallville study ran 25 LLM agents that formed relationships and organized events autonomously. The mechanism that made their behavior coherent over days was a three-part memory system: observation, scored retrieval, and periodic reflection.
Short-Term and Long-Term Memory for LLM Agents
An agent with no memory repeats itself. An agent with bad memory contradicts itself. Getting memory right means splitting it into kinds: short-term for the session, long-term for durable facts, procedural for how-to, episodic for what-happened.