Matt Pocock’s Agentic Engineering Workflow (just copy him)

David Ondrej interviews Matt Pocock of AI Hero about an agentic engineering workflow that delegates scoped implementation while keeping architecture, prioritization, product direction, and review under human control.

Key Points Covered

• Keep strategy human-owned: Pocock distinguishes tactical code production from strategic decisions about architecture, interfaces, tests, and task boundaries. AI can perform much of the former. Pocock says effective delegation still depends on the latter [00:00:00]-[00:02:52].
• Use skills as deliberate procedures: Pocock prefers user-invoked procedures such as Grill Me over automatically invoked abilities. This keeps the developer in control and avoids filling context with every skill description [00:17:00]-[00:21:51].
• Turn experience into reusable team workflows: Pocock says senior developers can package repeated planning and engineering processes as skills. Teammates can use and improve them. However, Pocock distinguishes reusable knowledge and skill from context-dependent wisdom [00:21:51]-[00:24:02].
• Isolate and parallelize AFK work: His setup combines local Claude Code planning with Sandcastle sandboxes and GitHub Actions for asynchronous implementation and review [00:24:51]-[00:26:59].
• Optimize the harness as well as the model: Pocock argues that prompts, skills, codebase architecture, tests, and feedback systems deserve as much attention as model choice. Developers can directly improve those conditions [00:27:47]-[00:32:34].
• Delegate tactics without delegating direction: Better models can complete broader scoped tasks, but Pocock says humans still need to set goals, judge whether results are correct, and retain product and roadmap decisions [00:33:38]-[00:36:49].
• Fix the system behind each defect: When a model finds a bug, the durable response is to strengthen recurring tests, security checks, or review processes rather than only patching that instance [00:38:54]-[00:41:50].
• Think in queues, not endless loops: He treats AFK development as multiple agents taking scoped tasks from a prioritized queue, with exploration, implementation, review, and merge represented as explicit stages [00:42:53]-[00:48:08].
• Preserve observability while reducing review cost: Pocock says human checkpoints can move later for lower-risk work. But maintainers still need sampled review and rich evidence. They need both to assess generated code and the system producing it [00:48:08]-[00:53:09].
• Rebuild the setup from a baseline: Pocock recommends removing accumulated skills, plugins, MCP servers, and instruction files, observing the uncustomized agent, then adding back only procedures that address demonstrated needs [01:00:05]-[01:02:02].

Full video: https://www.youtube.com/watch?v=nQwJVHCtDDY(opens in a new tab)