Coconuts Don’t Cut It: Understand Before You Adopt
Software engineering best practices only create value when they fit your team’s context, constraints, and actual problems.
Discover more
Memory Write Policies: When an Agent Should Remember and When It Should Not
Memory bugs in AI agents usually come from bad writes, not weak recall. Learn how to design write policies that decide what an agent should persist, when it should write, and when it should not.
How Retrieval Fits Into Agent Memory Without Becoming Memory Itself
Retrieval is not memory. In production AI agents for developers, retrieval should stay a read path to external systems, while memory remains a write path for learned continuity like preferences, instructions, and successful procedures.
Blackboards: Collaborate Through Shared Knowledge
The most adaptable systems are often built through collaboration, not strict sequencing.
Actors and Processes: Build with Independent Components
The easiest systems to scale are often the ones whose components know the least about each other.
Breaking Temporal Coupling: Design Beyond Sequence
Systems become fragile when correctness depends on invisible timing assumptions.
How to Build a Useful Eval Set for a Tool-Using Agent
Learn how to design an eval set for a tool-using agent using trace-level evaluation, dataset splits, layered scoring, and realistic failure cases that catch regressions before production.
Agent Evaluation and Tracing: Why Prompting Is Not Enough
Prompting can improve a single run, but it cannot prove that an agent workflow is reliable. This article explains how traces, scorecards, offline evals, and online monitoring turn agent quality into an engineering discipline.
Decoupling and the Law of Demeter: Talk Only to Your Friends
The less your code knows about its surroundings, the easier it is to change safely.
AI Agents for Developers: The Mental Model That Actually Holds Up
Most confusion about AI agents starts with weak definitions. This article explains the mental model that holds up in real systems: an agent is a control loop around an LLM with tools, state, and observable execution.