ARCHIVE
Library of Articles.
Every month's Agentic Design Library — preserved as published, organized by month. Each month: nine essays curated for operators thinking about how agents actually get built.
NOVEMBER 2026
9 essays
- · Building Effective Agents
- · Effective Context Engineering for AI Agents
- · Effective Harnesses for Long-Running Agents
- · Harness Engineering for Self-Improvement
- and 5 more →
OCTOBER 2026
6 essays
- · Brief independent investigation of agents' behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
- · AI Agents Push Humans Out of the Loop
- · Training a Misaligned Reward Seeker
- · Why I still haven't bought into true RSI
- and 2 more →
SEPTEMBER 2026
8 essays
- · Rewriting Bun in Rust
- · Measuring Reward-Seeking by Instilling Contrastive Beliefs
- · OpenAI's accidental cyberattack against Hugging Face is science fiction that happened
- · Incident Report: Unsanctioned Agent Behaviour During Cyber Testing
- and 4 more →
AUGUST 2026
7 essays
- · Harness Engineering for Self-Improvement
- · Securing the future of AI agents
- · Agentic Autonomy Levels
- · Understanding is the new bottleneck
- and 3 more →
JULY 2026
6 essays
- · The Twilight of the Chatbots
- · Vibe coding and agentic engineering are getting closer than I'd like
- · Patterns for Building Cybersecurity Evals
- · "It's Hard to Eval" Is a Product Smell
- and 2 more →
JUNE 2026
9 essays
- · How we contain Claude across products
- · Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contexts
- · How Agents Manage Other Agents: Four Subagents Patterns in 2026
- · Agent Harness Engineering
- and 5 more →
MAY 2026
8 essays
- · Harness design for long-running application development
- · How we built Claude Code auto mode: a safer way to skip permissions
- · Harness engineering for coding agent users
- · The Revenge of the Data Scientist
- and 4 more →
APRIL 2026
9 essays
- · Agent Harness for Large Language Model Agents: A Survey
- · Toward Architecture-Aware Evaluation Metrics for LLM Agents
- · Beyond Standard LLMs
- · Agentic Engineering: How Swarms of AI Agents Are Redefining Software Engineering
- and 5 more →
MARCH 2026
9 essays
- · LLM-Augmented Algorithmic Management: A Governance-Oriented Architecture
- · Managed Agents
- · Single Agents to AI Teams: The Rise of Multi-Agentic Systems
- · Fundamentals of Building Autonomous LLM Agents
- and 5 more →
FEBRUARY 2026
9 essays
- · Agentic Engineering Patterns
- · Agentic Engineering: How Swarms of AI Agents Are Redefining Software Engineering
- · Awesome AI Agent Papers
- · Building Effective AI Agents
- and 5 more →
JANUARY 2026
9 essays
- · LLM Architecture in 2026: What You Need to Know
- · Andrej Karpathy: The AI Workflow Shift
- · Awesome AI Agent Papers
- · Effective Context Engineering for AI Agents
- and 5 more →
DECEMBER 2025
9 essays
- · Software 3.0: Software in the Age of AI
- · 2025 LLM Year in Review
- · Karpathy's Sequoia Talk: 5 Predictions About Agentic Engineering
- · Single Agents to AI Teams: The Rise of Multi-Agentic Systems
- and 5 more →
NOVEMBER 2025
9 essays
- · Three Years from GPT-3 to Gemini 3
- · On Working with Wizards
- · Real AI Agents and Real Work
- · Agent Engineering
- and 5 more →
OCTOBER 2025
9 essays
- · Components of a Coding Agent
- · Fundamentals of Building Autonomous LLM Agents
- · Beyond Standard LLMs
- · Effective Context Engineering for AI Agents
- and 5 more →