Tag
A post recommending the open-source resource repository claude-code-best-practice, which compiles Claude Code’s core concepts, advanced features, 10 workflows, cross-model collaboration approaches, and 83 practical tips—a useful guide to avoiding pitfalls when developing complex projects.
Simon Willison highlights Jacob Sansbury's account of building Spawn, a multiplayer game world modified via prompts to the in-game agent Savi, which is now developed autonomously by a swarm of Fable-powered agents spending over $3M per month in tokens and shipping to production hourly.
讨论2026年AI算力市场的剧烈变化:价格上涨、合约期延长,以及智能体(agents)本身正成为算力的主要使用者,需要在同一工作流中同时使用GPU推理和CPU运行代码,呼吁更灵活的算力租赁方案。
Simon Willison quotes Geoffrey Huntley on enforcing AI coding agent behavior by using pre-commit hooks that block direct observability calls and inject prompts to make agents use his diagnostics library, achieving 'ten out of ten' results.
An in-depth breakdown of Lecture 5, "Agent Tools in Pictures," from Columbia University's Agentic Engineering course — 221 minutes covering the essence of tools, the complete call chain for a single invocation, five ways to package tools (functions / CLI / Skills / MCP / code execution), and security plus engineering judgment. The core thesis: "The model writes the order, the program does the cooking — prompts are not the lock, code is."
Kent C. Dodds reflects on the difficulty of teaching agentic engineering, noting that best practices for working with AI agents evolve so quickly that today's optimal approaches will soon be baked into the agents themselves.
A Warp essay argues that agentic engineering has split into 'product engineering' (humans ensuring quality and usefulness) and 'factory engineering' (deploying and optimizing agent swarms), and discusses the challenges and inevitable shift toward 'software factories' beyond prompt-driven development.
Victor Velazquez announces his new book 'The Agentic Engineer,' which outlines principles for building production systems with LLMs and includes real-world incident stories.
An announcement for a Birds of a Feather session on agentic engineering in San Francisco on October 14th, focusing on informal discussions and show-and-tell with builders and experimenters in the field.
This is a video tutorial on advanced agentic engineering, demonstrating how to use tools like first-mate to coordinate multiple AI models for high throughput parallel task processing.
Grok, an AI model, has created a configurable and downloadable encyclopedia for agentic engineering, including a field guide and integrated lessons, showcasing AI's ability to generate comprehensive educational resources.
Engineers at Thoughtworks conducted an experiment using AI agents in a monorepo to build an airline IROps system, discovering emergent coordination through shared plans and frequent commits.
The article emphasizes that effectively using coding agents requires skills in instructing them and verifying their work, which may involve more than traditional code review.
A tweet from David Ondrej recommending a repository that he believes every agentic engineer should use.
Wes McKinney explains how his three-person team at Kenn Software merges hundreds of PRs weekly using agentic engineering with tools like Superpowers and roborev, emphasizing human involvement in planning and design.
Addy Osmani highlights two AI adoption gaps among engineers: frontier users running many agents and companies that rarely use AI tools, advising the latter to start with one trusted loop.
Ray Fernando hosts a live broadcast masterclass on agentic engineering, covering graphs, verifiable runtimes, and zero-slop approaches.
This article presents an experiment on refactoring a large codebase written by AI agents, demonstrating that refactoring reduces token consumption for future AI-driven changes. The author details the methodology and results showing a decrease in input tokens after refactoring.
Stack Overflow explores why developers form deep trust in tools like Vim and Emacs, and how that trust is challenged by the rise of agentic AI coding tools, citing survey data showing AI usage up but trust down.
A developer shares how adding explicit anti-triggers to agent skills prevents conflicts between overlapping skills, ensuring consistent behavior.