@vikingmute: Great workflow, now it's also my main workflow for developing new features and new ideas: Grill - let AI fiercely question every detail until clear -> Research - separately analyze difficult areas and create a research document (optional) -> PRD - gen...
Summary
VikingMute shares their main workflow for developing new features and ideas: using AI (Grill) to drill down on details, Research to analyze difficulties, generating a PRD, breaking it into independent Issues, step-by-step implementation, and finally Review. This is a supplement to Matt Pocock's seven-stage AI development method.
View Cached Full Text
Cached at: 06/20/26, 10:25 PM
Great process, now it’s also my main workflow for developing new features and ideas:
Grill – let AI grill you on details until clear
-> Research – analyze problem areas separately and create a research document (optional)
-> PRD – generate a detailed requirements document
-> Issues – break the PRD into independent tickets with dependencies
-> Implement – code implementation, note: work independently, split into tickets + iterate to avoid too much context
-> Finally Review, verify
Matt Pocock (@mattpocockuk):
Here are my 7 phases of AI-powered development.I’ve been thinking that the pre-PRD phase needs more structure. You need to figure out the shape of the design tree first, before then walking down it with higher-fidelity prototypes.
In other words, /grill-with-docs needs to
Similar Articles
@shao__meng: Seven Stages of AI-Driven Development 1. Grill 2. Research 3. Prototype 4. PRD 5. Issues 6. Implement 7. Review From Skills For Real Engineers by @…
A Twitter thread shares the seven stages of AI-driven development from the Skills For Real Engineers project by @mattpocockuk, including alignment techniques like grill sessions and tooling for coding agents.
@shao__meng: Former Meta/Microsoft/Atlassian Staff Engineer's Agentic Engineering Workflow With this workflow @kunchenguid ships 40-50 tested production-grade PRs per day. He describes it: "You are the captain, agents are your crew…
Former Meta/Microsoft/Atlassian staff engineer Kun shares his agentic engineering workflow: centered on terminal, tmux, and Neovim, using global/project-level memory files and skills to train AI teammates, delivering 40-50 tested production PRs daily, boosted by voice input, AXI standard, Lavish interactive planning, and more.
@ThisisHan1_: Recently built a development pipeline and wanted to share the thinking behind it. I was inspired by loop/goal engineering and auto-goal (letting the agent write its own goals and spawn subtasks). But what really clicked for me was...
This development pipeline first creates a rough prototype to elicit user feedback, turning every 'that's not right' reaction into a checkable rule. Then AI agents independently develop and validate against those rules, catching issues early and avoiding self-deception.
@mattpocockuk: Here are my 7 phases of AI-powered development. I've been thinking that the pre-PRD phase needs more structure. You nee…
Matt Pocock shares his seven phases of AI-powered development, emphasizing the need for more structure in the pre-PRD phase.
@mattpocockuk: Going live, doing a full feature build using: - /grill-with-docs - /handoff - /prototype
Matt Pocock live streams building a 'delivery calendar' feature for his course video manager using AI tools like Grill with Docs. He focuses on aligning terminology and data models with AI agents, and discusses the importance of coding standards for agent experience (AX).