The closer we get to a reproducible cognitive framework, the more performant the software outcomes will get. I got significantly better results when I overlaid my cognitive framework Assess-Decide-Do on top of Claude Code. The model "understands" my mental state and plays along. That smooths the process and makes the development shorter and more robust. Repo link if you want to try: https://github.com/dragosroua/claude-assess-decide-do-mega-prompt
The closer we get to a reproducible cognitive framework, the more performant the software outcomes will get. I got significantly better results when I overlaid my cognitive framework Assess-Decide-Do on top of Claude Code. The model "understands" my mental state and plays along. That smooths the process and makes the development shorter and more robust. Repo link if you want to try: https://github.com/dragosroua/claude-assess-decide-do-mega-prompt
Very cool. Will check it out.
He's back! Good stuff, Matt. Going to re-read a few times and keep digesting as I work on my own workflow.
Thanks Brian! Trying to figure it out myself
been waiting 🥹