Free Lesson
Loop Engineering, Without the BS
30 min
Jul 28, 2026 7:00 PM
Virtual (Zoom)
In this video
What you'll learn
See the old pattern underneath the new name
Reduce loops to generate, score, revise, repeat, then compare them with search, gradient descent, and ordinary testing.
Know when a loop earns its token bill
Decide whether repeated model calls improve the result, save human time, or merely produce a larger token bill.
Stop agents from grading their own homework
Use held-out evals, separate access, human labels, and validation boundaries the agent cannot quietly rewrite.
Why this topic matters
Every agent workflow now wants a loop. Generate, judge, revise, repeat, and keep spending tokens until the chart goes up. Sometimes this is useful optimization. Sometimes it is an LLM grading its own homework with extra steps. We’ll separate the engineering from the hype, decide when a loop is worth running, and build eval boundaries that stop agents from rewriting the answer key.
You'll learn from
Hugo Bowne-Anderson
AI & data engineer, consultant, educator of 6+ million students (ex-Yale)
Coached teams at
