A self-optimizing prompting framework for Codex

This article is machine translated
Show original
ME AI Messages are structured prompts used to guide Codex in automatically analyzing its history to identify and solidify repetitive workflows. The framework requires Codex to review data such as sessions and Memories to identify repetitive, time-consuming tasks with clear reusability. Selection criteria include occurrence at least twice, stable input, and potential for efficiency improvements. Ultimately, Codex should create or extend existing assets in a minimal, practical form—such as a "skill," a sub-agent, or an automated tool—avoiding redundancy. The process includes generating a candidate list, performing the creation, and reporting results and items awaiting validation. (Source: ME)

Source
Disclaimer: The content above is only the author's opinion which does not represent any position of Followin, and is not intended as, and shall not be understood or construed as, investment advice from Followin.
Like
Add to Favorites
Comments