Where LLM Responsibility Ends
How a maintenance request generator separates model-written text, user requests, and rules the application enforces with ordinary code.
llm
When a Contract Test Knows Too Much
How LLMs can accelerate contract-test overengineering and why observable behavior matters more than implementation details.
Prompts Define the Work, Checks Define Done
Why the definition of done should move from prompts into a verifiable contract, with an independent review of the agent’s result.
Why the Second AI Agent Should Review Without the First Agent’s Context
Why independent review works better when the second agent sees the task and result but does not inherit the implementer’s explanation.
Why Verification Should Be Defined Before Implementation
Why acceptance criteria and verification methods should be defined before implementation, so that the meaning of done is not adjusted to fit the resulting solution.
AGENTS.md as Part of DocOps
Why AGENTS.md should be seen not only as AI instructions, but also as part of a DocOps approach to engineering context.
Why a Good AGENTS.md Is Rarely Long
Why AGENTS.md should stay short and not replace README, ADR, CHANGELOG, or project documentation.
AGENTS.md Is Short Project Memory
Why AGENTS.md is useful not only for AI, but also for returning to a project after some time.
What I Store in AGENTS.md
Which sections to keep in AGENTS.md so AI can understand the project quickly without turning it into another README.
How I Use AGENTS.md in My Projects
Why I keep AI agent instructions in the repository and how AGENTS.md helps preserve project context.