A senior Anthropic engineer just dropped 11-page PDF on "Loop Engineering" for agentic systems.
The shift: you stop prompting the agent. You build the system that prompts it instead.
Schedule → Discover → Build → Verify → Repeat
Every loop runs one turn, five moves:
• Discovery: it finds its own work - failing CI, open issues, recent commits - instead of being handed a list.
• Handoff: each task gets an isolated git worktree so parallel agents don't collide.
• Verification: a second agent, told to assume the code is broken, reviews the first. The "thing that can say no."
• Persistence: results get written to disk, never left in a context window that gets flushed.
• Scheduling: an automation wakes it on a timer. That's what makes it a loop.
The key insight: an agent grading its own work always praises it.
This 11-page PDF changed how I'm building agentic systems today.
Read it now, then explore the article below.
“只有当政府能够明确且可信地承诺允许企业破产时,市场纪律才能发挥作用。”
"We need a system in which insolvent firms fail. Market discipline only works if governments can demonstrably and credibly commit to allow firms to fail."
——现任美联储主席 Kevin Warsh 2010年在纽约大学斯特恩商学院的演讲
Anthropic engineer:
"At Antropic, >80% of our engineers are building with self-improving loops. in 3-6 months, it will be 100%.
my agentic loops can run for hours without spending hundreds of $$$."
in 30-minute podcast, an Antropic engineer shows how to build the right spec for an agentic loop.
Loop + plan + PRDs + spec + markdown - that’s the secret stack.
Worth more than a $500 agentic course on the internet.
Watch it now, then read how quants are building trading loops from scratch.