A synthesis of Mario Zechner's ideas on coding agents. Why the minimalism of the Pi agent, coupled with strict context engineering and CLI tools, often beats heavy frameworks.
Code Quality
A test suite can show good coverage and miss an obvious bug. To measure real quality, I look at four complementary axes, with a simple audit to apply to an existing project.
Once the spec is in place, I split the work between humans, AI, and deterministic tools. The critical test does not always come from the same author as the code, and the critic-agent often matters more than the writer-agent.
The first step in the AI workflow is specification. This article shows how I turn a vague user story into something a human and an agent can use without guessing, with Gherkin, typed examples, and properties.
The implicit promise of AI coding assistants was that tests would become a thing of the past. The reality documented by Kent Beck, ThoughtWorks, and several 2025 studies is the opposite: with AI, tests become essential — but the work has shifted.