Awesome Loop Engineering
Design loops, not just prompts.
Loop Engineering is the AI and coding-agent practice of designing recurring systems that discover work, delegate it to agents, verify results, persist state, decide next actions, and run again.
Canonical definition:
Loop Engineering is the AI and coding-agent practice of designing recurring systems that discover work, delegate it to agents, verify results, persist state, decide next actions, and run again on a cadence, event, or until a verifiable goal is reached.
The Stack
Prompt Engineering
What should I say to the model?
What should I say to the model?
Context Engineering
What state and knowledge should the model see?
What state and knowledge should the model see?
Harness Engineering
What tools, permissions, tests, and sandboxes surround one run?
What tools, permissions, tests, and sandboxes surround one run?
Loop Engineering
What recurring system governs agent work over time?
What recurring system governs agent work over time?
What The Repo Contains
- Curated papers, blogs, docs, tools, benchmarks, and patterns.
- Manifesto, taxonomy, comparison guide, and anti-patterns.
- Validated loop contract schema and example loop specs.
- Pattern library for PR, CI, docs, deploy, feedback, dependency, eval, security, cost, and bug-hunting loops.
Contribute
Share resources, corrections, or real loop patterns with trigger, intake, delegation, verification, state, budget, escalation, and receipts.
Field Guides
Understand the concept, boundaries, taxonomy, anti-patterns, and comparisons.