From 9c804e13ee5c4cd15a47891238194483406b59d0 Mon Sep 17 00:00:00 2001 From: Chaoyue He Date: Sun, 21 Jun 2026 12:49:42 +0800 Subject: [PATCH] Add loop-engineering topic --- topics/loop-engineering/index.md | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 topics/loop-engineering/index.md diff --git a/topics/loop-engineering/index.md b/topics/loop-engineering/index.md new file mode 100644 index 00000000000..0eee05b4bc3 --- /dev/null +++ b/topics/loop-engineering/index.md @@ -0,0 +1,8 @@ +--- +aliases: agent-loops, agentic-loops +display_name: Loop Engineering +related: ai-agents, llm, agentic-ai, automation, prompt-engineering +short_description: Designing recurring AI and coding-agent systems that discover work, verify results, persist state, and re-run over time. +topic: loop-engineering +--- +Loop Engineering is the practice of designing recurring AI-agent and coding-agent systems. Instead of prompting an agent turn by turn, you build a loop that discovers work, delegates it to one or more agents, verifies the result against tests or other deterministic gates, persists state outside the model, decides what happens next, and runs again on a cadence, an event, or until a verifiable goal is reached. It sits above prompt, context, and harness engineering: those improve a single run, while loop engineering governs repeated agent work over time, including budgets, retries, escalation to humans, and stopping conditions.