Harness Engineering for AI Agents
Why the system around the model may matter as much as the model itself—and how to engineer context, tools, state, verification, recovery, and control as one reliable execution environment.
Read articleOne+i journal · theme
Build & product
Practical notes on GenAI products, LLM applications, and agentic workflows.
Articles in this theme
5 articlesAgent sprawl is the new shadow IT: why enterprises need an agent registry
AI agents are gaining identities, credentials, memory, tools, and authority faster than many organizations can inventory or govern them. An agent registry is the first control plane primitive enterprises need.
Read articlePython Build Systems and Build Backends — Deep Practical Guide
A deep, practical guide to modern Python packaging, build frontends, build backends, artifact validation, native extensions, reproducibility, security, and architecture decisions.
Read articleSpec-Driven Development: the control plane for AI-native software engineering
Coding agents make implementation cheaper, not correctness automatic. A practical guide to using specifications, repository evidence, verification, and human decision gates to coordinate agentic software delivery.
Read articleDesigning agentic workflows people can trust
The product, governance, and human factors that make AI agents useful beyond the demo.
Read article