Start with one of these articles. Each one includes a prompt you can open directly in Claude or ChatGPT, or copy into another agent. You get the thinking behind the prompt and something practical to use on your own work.
I’ll keep adding to this page as I turn more of my practical work into prompts your agent can use.
Actual starting numbers for active work and queues, including solo and multiplayer spec-driven development, collaboration-pod topology, flow buffers, replenishment cadence, and historical WIP.
Open the article and promptA new open-source AI agent skill to help teams rewrite their work items from output/activity language to outcome-oriented language using a simple taxonomy.
Open the article and promptA follow-up AI coaching prompt for anyone who sat through my "Product Orientation Through LPM" talk — pressure-test one real initiative, find the real gap, and get one experiment to run in the next few weeks.
Open the article and promptFlow metrics are not useful because metrics are good. They are useful when important work is slow, blockers show up late, forecasts are fragile, and leaders need a better way to decide what to start, stop, finish, or fix.
Open the article and promptSeason 1 of Breaking the SAFe: where SAFe helps, where it goes sideways, and how practitioners can use Scrum first principles to course-correct before the framework becomes theater.
Open the article and prompt