@mattpocockuk: Writing ADR's for agents has been such a good decision Capturing all the non-obvious decisions in a codebase makes ever…
Summary
Matt Pocock recommends writing Architecture Decision Records (ADRs) for agents to capture non-obvious decisions, making agents in the stack smarter with minimal documentation.
View Cached Full Text
Cached at: 05/30/26, 04:03 AM
Writing ADR’s for agents has been such a good decision
Capturing all the non-obvious decisions in a codebase makes every agent in your stack that touches the stack smarter
It’s the thinnest layer of docs that captures the stuff code can’t
Similar Articles
@mattpocockuk: Another layer of documentation I'm considering (along with CONTEXT.md and ADR's) is a list of all the agreed test seams…
Matt Pocock proposes documenting agreed test seams in apps, arguing that AI agents cannot be trusted to make good testing decisions, often leading to fragile tests that break on implementation changes.
@elldeeone: Have been using @mattpocockuk's /improve-codebase-architecture skill now for a couple of months and it's amazing. I don…
Matt Pocock's repository of agent skills for coding assistants improves codebase architecture and developer alignment.
I'd like to share an updated methodology for building agents.[P]
Introduces Spice, an open-source decision layer that acts as a 'brain' above execution agents like Claude Code and Codex, enabling context-aware task delegation and structured decision-making.
@yoheinakajima: great article, mostly focused on coding agents but applies elsewhere impo. aligns w a lot of my prior thoughts: - agent…
A tweet highlighting key principles for building agent systems, emphasizing scaffolding, memory, and reusable tools, based on an article by Yohei Nakajima.
@dair_ai: If you design production agent systems, this matters. Most devs accidentally let their framework defaults make critical…
This paper introduces the concept of the stochastic-deterministic boundary (SDB) for production LLM agents and provides a methodology for selecting architectural patterns to improve reliability and performance.