loop-engineering

Andrew Ng discusses the concept of 'loop engineering' as a key approach for building AI agents to develop software iteratively, outlining three main loops: agentic coding loop, developer feedback loop, and external feedback loop.

A leaked internal Anthropic playbook details loop engineering principles for maximizing AI productivity, including separating generator and evaluator, using worktrees, and an 80/20 barbell cost strategy.

A tweet noting that loop engineering is essentially prompt engineering with good system design.

A new paradigm called loop engineering is introduced, shifting from manual prompt engineering to designing systems that autonomously prompt AI agents. The GitHub repository provides patterns, quickstarts, and npm packages for implementing loops with coding agents like Grok, Claude Code, and Cursor.

Explains loop engineering as a shift from manual prompting to autonomous AI loops that run tasks and only involve humans when needed, popularized by Claude Code's creator Boris Cherny.

An article demonstrating how to build a loop that automatically tunes RAG system configurations to achieve a target recall, including full code and evaluation methods.

A guide on building autonomous loops for AI coding agents, explaining how to design systems that allow agents to run tasks repeatedly without manual intervention, with conditions for when loops are worth it and how to build them safely.

The article discusses three key loops for building AI-powered software products: the agentic coding loop, developer feedback loop, and external feedback loop. It highlights how loop engineering enables AI agents to iterate autonomously and developers to focus on higher-level decisions.

A senior Anthropic engineer released an 11-page PDF on Loop Engineering, detailing a framework for building autonomous AI agent systems that self-discover work, isolate tasks, verify through a second agent, persist to disk, and run on a schedule.

This article introduces six ways to use Hooks in Claude Code, including permission pop-ups, startup schedule announcements, summary cards, automatic file organization, sedentary reminders, and long task notifications, demonstrating how event-driven automation can improve the efficiency of AI workflows.

At the Generative AI Developer Conference, ihower shared about the Harness + Loop Engineering series of articles and slides for Agent development.

The article declares Prompt Engineering dead, proposes Loop Engineering as the new paradigm for AI development in 2026, emphasizes designing autonomous loop systems (Plan-Execute-Verify-Iterate) to let agents autonomously complete complex workflows, and provides practical examples and a getting-started approach.

A senior Anthropic engineer published an 11-page paper on Loop Engineering, proposing a new paradigm for building agentic systems centered on feedback loops, isolation, verification, and memory rather than smarter prompts.

A detailed breakdown of loop engineering for AI agents: moving from manual agent supervision to autonomous loops with triggers, makers, checkers, and persistent state. Recommends Zep's Graphiti for temporal knowledge graphs and Comet's Opik for observability to build reliable unattended agent systems.

This article discusses the application of Loop Engineering in AI agent workflows, focusing on Anatoli Kopadze's detailed explanation of loops and Peter Steinberger's talk at AI Engineer Europe, emphasizing the importance of automated verification loops and acceptance criteria.

Google engineers propose the Loop Engineering method, using LLMs to generate code transformation proposals, leveraging compiler feedback as an automatic reward signal to achieve a code optimization iteration loop without human annotation.

Kent C. Dodds introduces the concept and practice of 'Loop Engineering': setting triggers, action/observation loops, and stop conditions for coding agents to autonomously complete multiple rounds of work, replacing manual prompts with automated events to boost development efficiency.

A senior Google engineer released a 19-page PDF on 'Loop Engineering' for LLM and agentic systems, outlining an iterative feedback loop where the LLM proposes code transformations, observes compiler feedback, learns from it, and repeats until improvements stop.

This article describes the loop engineering cycle for AI Product Managers, emphasizing building reusable systems that improve over time rather than one-off prompts.

This article explains the concept of loop engineering in AI agents, emphasizing that the core loop is trivial but the critical work lies in the harness around the model, including knowing when to stop and preventing context rot.