For longer-running tasks, it's helpful to give coding agents a form of short-term memory. This keeps the agent on task by keeping the most important items in context. This is a README in the root of a blank folder called agent-helpers that has subfolders and a scratchpad.

This prompt is an example of how to get an AI coding agent to work through a long-running task. Previously I had worked with ChatGPT to come up with a very long list of tasks that needed to be done. I also created a blank file called `scratchpad.md` that keeps track of the status

After I write user stories, I turn them into a development checklist. I use this prompt to then incrementally go through the checklist, keeping track of progress as we go.

I use this prompt to review my build checklist before I start LLM-driven development. It helps ensure that Cursor (or another agent) has clear instructions that accomplish my sprint goals and adhere to my styles.