NewsletterBlogLearnCompareTopicsGlossary

Blog

In-depth articles on AI models, tools, and engineering practices.

4 min read

OpenAI's Technical Lessons From Building Computer Access for Agents

OpenAI shares key engineering lessons from building computer access for agents: tighter execution loops, file system context, and secure network access.

DEV
4 min read

OpenAI's Chain-of-Thought Controllability Eval: What It Measures and Why It Matters

OpenAI releases a Chain-of-Thought Controllability evaluation to measure how well reasoning models follow instructions within their thinking process.

MODEL
5 min read

Obsidian + Claude Code: Building a Second Brain That Actually Works

How pairing Obsidian's local markdown vault with Claude Code's file-aware agent creates a persistent, controllable context system that solves AI's biggest usability problem.

TECHNIQUE
4 min read

MCP vs CLI vs Skills: How to Extend Claude Code Without Over-Engineering

Compare MCP servers, CLI tools, and Skills — the three ways to extend Claude Code. Learn when each fits and avoid the over-engineering trap.

DEV
5 min read

Lessons from Building Claude Code: How Anthropic Designs Agent Tools

How Anthropic's Claude Code team designs agent tools by 'seeing like an agent' — lessons on elicitation, task management, and self-directed search.

DEV
5 min read

Harness Engineering: How LangChain's Coding Agent Jumped from Top 30 to Top 5

LangChain improved their coding agent 13.7 points on Terminal Bench 2.0 by changing only the harness — not the model. Here's how self-verification, tracing, and prompt tuning made the difference.

DEV
5 min read

Claude Code: Key Benefits and Features That Matter

Claude Code's key benefits and features explained — agentic file editing, smart debugging, git automation, and why benefits drive adoption more than specs.

tools
4 min read

Spec-Driven Development: Why Specifications Are the New Code for AI Agents

Spec-Driven Development (SDD) front-loads thinking into detailed specifications so AI coding agents build the right thing first time. Here's how the three-level framework works.

DEV
4 min read

How Intercom Built 13 Claude Code Plugins With 100+ Skills and Hooks

Intercom engineered an internal Claude Code plugin system with 13 plugins, 100+ skills, and hooks — here's what it reveals about enterprise AI tooling.

DEV
4 min read

How to Integrate Claude Code into Your Development Workflow

Claude Code shifts AI coding from autocomplete to autonomous agent. Here's how to integrate it into your real development workflow.

tools
8 min read

How to Integrate an MCP Server: A Step-by-Step Guide for AI-Powered Tool Access

Learn how to integrate an MCP server with Claude Code and other AI clients — from configuration to testing and production deployment.

tools
7 min read

How to Effectively Prompt Claude Code: A Practical Guide

Learn how to effectively prompt Claude Code with structured instructions, CLAUDE.md files, and skill-based workflows for faster, more reliable results.

tools