An atlas of AI engineering notes
170 articles charted into five districts. Drag the map, or open the index.
Agents
- Deep Dive: How Plannotator Turns an Agent Hook Into a Human Review Loop
- Deep Dive: How NVIDIA SkillEvaluator Predicts Whether Your Agent Skill Will Even Load
- On GitHub Trending: Tencent Open-Sources LoopForge, a Cloud-Based Self-Evolving R&D Platform (English Translation)
- Deep Dive: How AG-UI Turns Every Agent into One Typed Event Stream
- Deep Dive: How chrome-devtools-mcp Gives Agents a Browser Without Drowning Them in Data
- Deep Dive: How msitarzewski/agency-agents Turns 283 Markdown Personas into a Multi-Tool Agent Team
- Deep Dive: How garrytan/gbrain Turns Agent Memory into Seven Frozen Verbs
- Building an Enterprise-Grade Agent OS on Hermes: 200+ Automated Tasks a Day (English Translation)
- Anthropic's 24/7 Always-On Agent Architecture Guide: Inbox, Timers, Memory, Permissions, Outbox (English Translation)
- Building Always-On Agents: Five Primitives from Anthropic's Architecture Guide
- Flint-interactive: Giving Agents a Language for Interactive Charts
- How Microsoft Evaluates Copilot Without Touching Customer Data
- PDD Kit: Formally Verifying What Your Coding Agent Wrote
- Lazarus: Backdooring an AI Agent by Reprogramming Fewer Than 10 Neurons
- Deep Dive: How alibaba/open-code-review Splits Code Review Between Deterministic Code and an Agent
- Deep Dive: How openai/codex-security Turns a Security Audit into Skills and a CLI
- Deep Dive: How addyosmani/agent-skills Turns Engineering Discipline into Skills
- Deep Dive: The Agent Loop Inside anthropics/claude-quickstarts
- Living Notes: The MCP Skills Over MCP Working Group, Meeting by Meeting
- Deep Dive: How obra/superpowers Forces a Disciplined Agent Workflow
- Deep Dive: Why mattpocock/skills Makes Your Agent Interview You First
- Deep Dive: Inside anthropics/skills and the Progressive Disclosure Design
- Deep Dive: How agent-browser Lets an Agent Drive Chrome with Snapshots and Refs
- Training UI Agents on Live iOS Apps: Apple's Planning-Grounding Approach
- Anthropic's AI for Science Goes Institutional: 20 Partners, One Shared Bet
- Testing Agent Skills Properly: Building a Skill That Evaluates Other Skills
- Agent Skills Goes Neutral: Anthropic Donates the Standard to the Agentic AI Foundation
- Scion: Why Anthropic Replaced Git for a Monorepo Written by Agents
- When Claude Broke Containment: Three Real-World Incidents from Cybersecurity Evals
- Claude Opus 5: State-of-the-Art at Half the Price
- Congress Wants an AI Kill Switch. Google's Data Shows the Gap Between Fear and Reality.
- Steering Claude Code: The 7 Instruction Methods That Actually Matter
- Mapping a Year of AI-Enabled Cyber Threats: Insights from Anthropic's Red Team
- Claude Opus 4.8 feels like an agent-quality upgrade, not just a benchmark bump
- Self‑Evolving Skills: Train Agent Skills Like Models
- How Anthropic contains Claude—and what that means for agentic AI
- Google I/O 2026: Gemini 3.5 Flash and What '3.2 Quadrillion Tokens a Month' Actually Means
- The AI Native Org Shift: What Alibaba's Engineers Are Actually Worried About
- The 34% Problem: What Microsoft Research Reveals About AI Agents You Trust with Real Work
- The First Java Harness Framework Is Here | AgentScope Brings OpenClaw to Enterprise Distributed Scenarios
- ByteDance Interviewer: Your SFT Accuracy is 94%? Then Why Can't Your Agent Complete 10 Steps?
- LLMs Corrupt Your Documents When You Delegate: What the DELEGATE-52 Benchmark Reveals
- Claude Goes to Work in Finance: 10 Agent Templates, Excel/PowerPoint Add-ins, and Autonomous Deal Pipelines
- Anthropic's Managed Agents: What It Means to Run AI That Runs Itself
- Hermes Agent: The Self-Improving AI That Actually Learns
- Harness Engineering: Anthropic's Practical Guide to Building Production AI Agents
- Inside Claude Code: A Deep Architecture Analysis of 4,756 Source Files
- The Anatomy of an Agent Harness
- How Anthropic Built Their Multi-Agent Research System: Architecture Lessons from Production
- NVIDIA NemoClaw: Enterprise-Grade Security for Autonomous AI Agents
- OpenClaw 3.12: Major UI Overhaul, Speed Boost, and Enhanced Stability
- The AI Coding Wars Heat Up: Claude Opus 4.6 vs GPT-5.3-Codex
Drag to explore. Arrow keys pan. Tab visits pins.