An engineer's recipe for AI self-improvement: scheduled MCP automations that fix the codebase, not bugs

DanielLockyer · x · 2026-09-13

Daniel Lockyer describes his version of "AI recursive self-improvement": scheduled automations with MCP access that continuously inspect errors, traces, and logs, then ship improvements to the codebase so the whole system gets faster.

The key, he argues, is not fixing individual bugs but operating at the meta level — finding the small number of high-leverage changes. Examples: attaching user IDs to errors for easier bug reproduction, or instrumenting parts of the code for performance — making future bugs trivial to fix.

Related event: Developer Combines Scheduled Automations with MCP for Recursive AI Self-Improvement(2 posts)→

Original post →

More from coding & agent

coding & agent channel →