The PAPI Field Guide
A library, not a feed: guides for switching tools, methodology worth stealing, and honest notes from running PAPI on its own development.
Switching guides2 guides
Switching from Lovable to PAPI
Lovable is great at zero to one. This is a guide to what happens after one: the wall every prompt-built project hits, and how to graduate without losing the plot.
Switching AI Coding Tools Without Starting Over
Moving from Cursor to Claude Code, or anywhere to anywhere, means losing everything that lived in the chat. Why the migration hurts, why context files are a copy of a copy, and what changes when the project holds its own state.
Methodology4 guides
Why Your AI Forgets Your Project
Every session starts cold. The re-explaining tax is real, and a longer chat history does not fix it. What project memory should actually mean.
Plan, Build, Review: The Loop That Compounds
AI projects start fast and decay. The fix is not a better prompt, it is a loop: plan, build, review, release, where every build makes the next plan smarter.
Architecture Decisions Don't Survive AI Speed
Code records what got built, never why. Architecture decision records were the right instinct, but they rot. What a decision looks like when it stays alive, and why your AI assistant needs that more than you do.
Loop Engineering: Why AI Workflows Spin Instead of Compound
Most AI coding workflows have the shape of a loop and behave like a circle. The step everyone skips, the second loop almost nobody runs, and where the compounding actually shows up.