Skip to content
RosmarOps
  • Blog
  • About
  • Observatory
  • RosmarOps, the product
  • ES
  • CA

Loop engineering

What happens when you leave an AI agent working in a loop: what starts it, who checks what it does, when it stops and what it costs. With dated studies and cases, and their sources.

Loop engineering: letting agents work on their own doesn’t mean they work better

November 8, 2026 by Albert Garcia Pujadas
An AI agent at the centre of a loop of documents going round, with a hand checking one of them with a magnifying glass.

A study examined 36,487 software repositories and confirmed autonomous AI agent loops in 217. More interesting than the percentage is what we know —and what we still don’t— about the controls and results of those systems.

Categories Loop engineering Tags Claude Code, Codex

Recent posts

  • Loop engineering: letting agents work on their own doesn’t mean they work better
  • What wasn’t read doesn’t count as clean
  • Tools that check what your AI coding agents can reach (October 2026)
  • Can one AI agent change another agent’s configuration?
  • Which keys can your AI coding agent read?

© 2026 RosmarOps

© 2026 RosmarOps • Built with GeneratePress

Cookie settings