Harness engineering is the discipline of designing the environments, constraints, and feedback loops around AI coding agents that make them reliable at scale. The formula is: Agent = Model + Harness. Harness is everything that isn't the model: the infrastructure that governs how the agent operates, what it can access, and how it self-corrects.
In this article I'm collecting all the technologies I stumbled upon while researching harness engineering. The list is not exhaustive, but it should give you a good starting point to explore the landscape. This aims to be a living document, so I'll keep it updated.
high quality version of the technology landscape
SDD
Orchestration
AST and Code Parsers
Sandboxes
Working with skills
Skill Reference
Skill Syntax Validation
Skill Dependency Management
Skill Security Scanners
Knowledge Base
- Introducing the Open Knowledge Format (Google Cloud Blog)
- How to Build Karpathy's LLM Wiki (Starmorph)
- LLM Wiki (Karpathy Gist)
Top comments (0)