In the previous post I toured Herdr and how I lay it out: one space per folder, one tab per kind of work, agents in tall columns, shells in short stacks, all of it spread across a 5120×1440 ultrawide. That’s the what. This one is the why, and then the part that actually decides whether... Continue reading →

Herdr is a terminal workspace manager designed for AI coding agents, enhancing productivity by organizing terminal sessions. It allows users to manage multiple agents efficiently, offering features like session handling, workspace creation, and agent state detection. Users can visually monitor agents’ statuses, prioritizing those needing input, facilitating seamless coding processes. Continue reading →

Creating a notes repository alongside code repositories enhances project clarity and continuity. It serves as a durable knowledge base for plans, decisions, and team structures, accessible to both human team members and agents. This organized approach minimizes miscommunication and maintains project focus, ensuring everyone stays aligned and informed throughout the development process. Continue reading →

The content discusses the complexities of implementing feature toggles in software development, using three examples: a data pipeline switch, an expedited shipping offer, and a saved filters interface. It emphasizes understanding ownership, failure modes, and scope, and highlights the importance of maintaining clear boundaries and decision-making processes to prevent confusion and errors during development. Continue reading →

Getting a coding agent productive is less about the prompt and more about whether the machine in front of it can actually build, run, and reach the systems the work depends on. Cursor, Claude, Codex, and the rest are fast when the local world is already honest: dependencies install, the app boots, tests can run,... Continue reading →