My Agent Called a Failed API 5 Times—The Bug Wasn't in the Code
When an agent repeats the same failing API call, code review won't help. Traces are the new source code for debugging AI agents.
← Index
AI Agents & Developer Tools
Deep coverage of AI agent architecture, context engineering, and developer workflows.
40 posts
I Was Too Lazy to Write CLAUDE.md — Turns Out That Was the Right Call
New benchmark data shows AGENTS.md and CLAUDE.md context files actually hurt coding agent performance. Sometimes laziness is the best engineering decision.
4 Updates from Anthropic, OpenAI, and Google: The Hidden Pattern
Three companies updated their coding agents at the same time. The directions overlap. The real battleground isn't models; it's how fast they absorb developer workflows.
5 AI Predictions for 2026: Agents, Chips, and Historic Exits
From the SaaSpocalypse to model-specific silicon, five bold predictions for where AI is heading in 2026, with roughly 50% confidence of getting them right.
The Cache Design That Cuts Claude Code API Costs by 90%
My API costs jumped 10x when the cache broke in production. The same day, Anthropic engineers explained exactly why.
From 6.7% to 68.3% Task Success: The Harness Made the 10x Difference, Not the Model
What LangChain's Terminal Bench results and the hashline format experiment revealed. The same model flipped leaderboard rankings, and the reasons came down to three things: prompts, tools, and middleware.
The Web's Top Customer Is Shifting from Humans to AI
From Cloudflare and Vercel's Markdown for Agents to Google's WebMCP, reading and writing are being standardized simultaneously, ushering in the Agent-Native Web era.
5 SKILL.md Body Writing Rules Hidden in Anthropic's Docs
Five SKILL.md body writing principles buried in Anthropic's official documentation. From separating description and body roles to embedding verification loops.
Why OpenAI Hired the OpenClaw Creator - The AI-Native Messenger Era Begins
Peter Steinberger joining OpenAI isn't just a talent grab. It signals the dawn of AI-native messengers that could redefine how we communicate.
How OpenAI Built 1 Million Lines of Code Using Only Agents: 5 Harness Engineering Principles
OpenAI's Codex team built a 1M-line codebase using only AI agents. Here are the five harness engineering principles they discovered along the way.
Claude Code Agent Teams - From Setup to Shortcuts
A practical guide to Claude Code's new multi-agent teams feature: activation, keyboard shortcuts, terminal compatibility, task management, and known limitations.
OpenAI & Google's 2026 Declaration: The AI Price War Has Begun, and Now Is the Best Time to Jump In
OpenAI and Google are racing to launch affordable AI plans while Chinese competitors shatter price floors. Here's why this moment is your best entry point.
The AI Wrapper Era Is Over. The Age of Claude Agent Wrappers Has Begun.
Anthropic's Tariq Shihipar breaks down what it actually takes to build production-grade agents - from Bash-first tooling to file-system-driven context engineering.
Claude Code Was for Developers - Cowork Is for Everyone
Anthropic launches Cowork, an autonomous agent that reads, edits, and creates files on your local machine. Vibe coding meets vibe working.
ChatGPT Is Android, Claude Is iOS
Why $300B evaporated from SaaS stocks as ChatGPT and Claude race to become the AI app store - and what the 2008 mobile wars tell us about what comes next.
How the Creator of Claude Code Actually Uses Claude Code
Boris Cherny's workflow hit 5K likes in 2 hours. His setup is simpler than you'd expect - parallel sessions, plan mode, CLAUDE.md, and verification loops.
The Claude Code Setup Guide That Made Me Rethink Everything
An Anthropic hackathon winner's 10-month Claude Code configuration - context management, hooks, subagents, and the principles that actually matter.
Claude Code Skills Setup: 1 Person Doing the Work of 30
Six Claude Code skill combinations that let a small team run a full-stack business - from marketing and video to UI design and code quality.
4 Claude Code Skills That Actually Survived Out of 100K
After installing hundreds of AI coding agent skills, only 4 made it into my daily workflow. Here's what survived the weekend audit.
What Claude Code's Task System Reveals About the AI-Native Engineer
Claude Code renamed Todo to Task. It looks like a small change, but it marks the beginning of a completely different system - one built for AI swarms.
Claude HUD: The Plugin That Made AI Agents Observable
A game-style status bar for Claude Code that shows context usage, active tools, sub-agents, and todo progress in real time.
The Weekend Clawdbot Sold Out the Mac Mini - and Why Kakao Should Be Worried
Clawdbot proved that AI agents running locally on your own hardware can replace messenger apps. Here's why that threatens every chat platform.
Context7: Use Skills and Subagents, Not Just MCP
Connecting Context7 via MCP floods your main context with docs. Skills and subagents isolate queries, keeping long coding sessions stable.
Every App Becomes an API in the Age of Personal Agents
Why YC and OpenClaw leaders believe software is being rebuilt for agents - and what it means for developers building products right now.
Everything Is Becoming a Skill: AI Is Now the One Using Your Service
With AI reading 50% of developer docs and bot traffic outpacing humans 3-to-1, services are racing to package their knowledge as agent skills. Here's what's driving the shift.
Karpathy's Wake-Up Call: The New Abstraction Layer Every Developer Must Learn
Andrej Karpathy admits he's never felt this behind as a developer. Here's the new AI agent abstraction layer he says you must master - or risk falling 10x behind.
Meta's $2.5B Manus Acquisition - Its Core Tech Is Now Open Source
The file-based memory system behind Manus's $2.5 billion valuation is now a free Claude Code skill. Here's why it matters for every AI agent builder.
Manus Acquired by Meta for $300M Reveals Core Agent Development Principles with LangChain
Manus shared the hard-won lessons behind building production AI agents - from context rot to evaluation rethinking - in a joint presentation with LangChain.
Inside the $3.6B Secret Behind Manus: Why AI Agents Actually Fail
Meta acquired Manus for $3.6 billion. The secret wasn't a bigger model - it was context engineering. Here's what most AI agents get wrong.
Multi-Agent Architecture: Splitting Blindly Will Backfire
Not all multi-agent patterns are equal. Learn when subagents, skills, handoffs, and routers actually outperform a single agent - with real scenarios and numbers.
The One Article That Unblocked My Multi-Agent Architecture
Orchestration patterns, communication methods, memory management, and production pitfalls - a practical breakdown of everything I struggled with when designing multi-agent systems.
Dissecting Oh-My-OpenCode and the Future of Context Engineering
A deep dive into Oh-My-OpenCode's multi-agent orchestration architecture - how programmatic context isolation, parallel execution, and evidence-based research are redefining what AI coding agents can do.
7 Building Blocks of AI Agent Design, Learned from Opencode Docs
Opencode's open-source documentation doubles as an introductory guide to agent architecture. Here are the seven core concepts every developer should understand.
The Era of AI Deploying Production Code Overnight
How a Claude Code plugin named after Ralph Wiggum is redefining autonomous coding through iterative loops, memory architecture, and stop hooks.
6 AI Agent Trends Established Worldwide in January 2026
Six battle-tested AI agent patterns that emerged globally in one month - from persistent loops to multi-agent orchestration.
6 Principles of AI Agent Development Established Globally in One Week
Context engineering took the world by storm in early 2026. Here are six battle-tested principles from Manus, Cursor, and Claude Code that define modern AI agent development.
10 Principles of AI Coding from the OpenClaw Creator
Peter Steinberger, who built GitHub's fastest-starred project, shares 10 hard-won principles for working with AI coding agents.
Why Claude Code Dropped Todos and Slash Commands
Anthropic replaced TodoWrite with Tasks and Slash Commands with Skills in two days. Both changes point in the same direction - unhobbling the model.
Will UI Really Disappear in the AI Era of 2026?
Claude Code and AI avatar apps prove users want results, not complex interfaces. The Zero UI era is approaching faster than we think.
My Terminal Setup for AI Agentic Coding
How I use Ghostty, Yazi, Fish, and LazyGit to run multiple AI agents in parallel - a lightweight terminal stack built for agentic workflows.