The AI engineering community has adopted the term 'loop' to describe at least four distinct architectures: execution loops for agent decision-making, task loops that restart agents until tests pass, p…
Software engineers are producing unprecedented technical debt as AI coding tools accelerate sloppy code generation, with research showing a 20% drop in junior developer employment and 30-40% more tech…
Boris Cherny, creator of Claude Code at Anthropic, introduced /goal and /loop commands that enable autonomous AI agents to work without human intervention, shifting the paradigm from prompting to loop…
Prompt engineering is being replaced by loop engineering, a practice where AI systems generate, evaluate, and improve their own work until meeting a goal. Engineers at Anthropic and OpenAI are now des…
Anthropic released Claude Code, a terminal-based AI agent that has captured 4% of all public GitHub commits and generates over $500 million in annual run-rate revenue. Built with TypeScript, React, In…
A developer traces the evolution of AI interaction design from prompt engineering (2022-2024) through context engineering (mid-2025) to loop engineering (June 2026), arguing each rename reflects a gen…
Boris Cherny, creator of Claude Code at Anthropic, stated in 2026 that his job is now to write loops rather than prompt models directly. A developer at Puzzle Quest Games describes the bootstrap probl…
Loop engineering, where developers define loops that prompt coding agents until a task is complete, is gaining attention from figures like Peter Steinberger and Boris Cherny. However, the approach fac…
Boris Cherny, head of Claude Code, advocates replacing manual prompting with agent loops that automate coding tasks. Bun's team used such loops to rewrite 750,000 lines of code in 11 days with 99.8% t…
Anthropic's Claude Mac app is built with Electron instead of native code, a decision tech commentator John Gruber attributes to engineering lead Felix Rieseberg, a co-maintainer of Electron. Gruber's …
Running multiple Claude Code sessions via tmux, git worktrees, and shell scripts works for two or three agents but breaks at scale due to no routing, shared memory, budgets, or crash recovery, accordi…
Andrew Ng introduces three key loops for building 0-to-1 products with AI agents: the agentic coding loop, developer feedback loop, and external feedback loop. He argues that humans retain a context a…
Agent loops fail in production due to state management issues in the database, not model quality, according to a CockroachDB analysis. Common failures include inconsistent state, interrupted writes, a…
A developer named Shivansh Pandey created a Claude Code skill called loop-engineering that automates the process of setting up loop engineering in a repository. Loop engineering replaces manual step-b…
Andrej Karpathy's AI coding rules, The Batch's 'loop engineering' issue, and Claude Code lead Boris Cherny's flat org structure signal that the unit of AI work has shifted from prompts to self-correct…
Boris Cherny, an engineer at Anthropic, identified five archetypes for future product roles—Prototyper, Builder, Sweeper, Grower, and Maintainer—based on observations of the Claude Code team. He argue…
Cursor launched an iOS app that lets developers launch and manage AI coding agents from their phone, connecting to the desktop version for remote supervision. The move signals a shift toward mobile-fi…
Cursor launched a mobile app for iOS that lets users prompt coding agents from their phone, following similar moves by Anthropic and OpenAI. The app integrates with Cursor 2.0's agent-based coding sys…
Claude Code creator Boris Cherny outlined five job archetypes for the AI era—Prototyper, Builder, Sweeper, Grower, and Maintainer—arguing that traditional engineering, product, and design roles are me…
Boris Cherny of Anthropic, Peter Steinberger, and Addy Osmani of Google are promoting 'loop engineering,' a workflow where developers design automated loops that prompt AI agents instead of typing pro…