Building agents — AI agent development

The engineering itself: agent architecture patterns, tool calling that does not hallucinate arguments, memory that stays relevant, retrieval that grounds answers, and multi-agent systems that are worth the complexity.

5 guides

Multi-Agent Systems: When Several Agents Beat One

Multiple agents help when subtasks are genuinely independent and need different tools. Otherwise you have bought latency, cost and a failure surface nobody can trace.

Building agents 9 min read

RAG for Agents: Grounding Answers Without Drowning in Context

Retrieval as a tool the agent chooses to call beats retrieval bolted to the front of every request. Chunk for meaning, cite the source, and let the agent say it found nothing.

Building agents 9 min read

Memory in AI Agents: What to Keep, Compress and Throw Away

Agents do not have memory; they have whatever you put back into the context. Four tiers — goal, recent, compressed, retrieved — solve most of it.

Building agents 9 min read

Tool Calling: How to Design Tools an Agent Uses Correctly

Most agent failures are tool design failures. Narrow scope, typed arguments, honest errors and idempotency fix more than any prompt rewrite will.

Building agents 9 min read

AI Agent Architecture: The Patterns That Hold Up in Production

Six patterns cover almost every production agent: bounded loop, planner-executor, critic pass, tool gateway, memory tiers and human gate. Here is when each earns its place.

Building agents 9 min read

Scope a build