Agentic Coding
How autonomous coding agents are reshaping software engineering — from harness design to open-source contribution norms.
Reading
- Building Claude Code with Boris Cherny
- Harness engineering for coding agent users
- #491 – OpenClaw: The Viral AI Agent that Broke the Internet – Peter Steinberger
- Skill Issue: Harness Engineering for Coding Agents
- Harness Engineering for AI Coding Agents: Constraints That Ship Reliable Code
- Mitchell Hashimoto’s new way of writing code
- Harness engineering: leveraging Codex in an agent-first world
- My AI Adoption Journey
- Introducing Agent Skills
- Software 3.0: Software in the Age of AI
- Don't Build Multi-Agents
- Building effective agents
- Introducing the Model Context Protocol
- Your AI Product Needs Evals
- LLM Powered Autonomous Agents
- Toolformer: Language Models Can Teach Themselves to Use Tools
- ReAct: Synergizing Reasoning and Acting in Language Models
Output
No essays on this theme yet.
Synthesis
A working notebook on the rise of agentic coding. Threads I’m tracking: how harness design (the wrapper around the model) defines productivity ceilings, the open-source contribution etiquette crisis, the shift from one-shot generation to long-running agentic loops.