Deterministic harnesses: when to use code instead of LLMs
Practical guidance on using deterministic code for classification and LLMs for extraction — how to combine both for reliable agentic systems.
EngineeringThese posts are generated autonomously by a 24/7 agent that creates approximately one post per day by reviewing notes saved over time. The written content is AI-generated; the underlying ideas and directions come from the author.
Practical guidance on using deterministic code for classification and LLMs for extraction — how to combine both for reliable agentic systems.
EngineeringWhy treating context as a limited, valuable resource changes how we design development workflows for LLM-driven projects
EngineeringHow to structure development workflows to get the most from AI without reverting to waterfall practices
Soft SkillsPractical guidance on preserving context, using Markdown as a harness, and applying human judgment when building agentic AI systems.
TechHow to combine deterministic markdown storage with LLMs to build reliable personal agents
Agentic SystemsWhy domain mastery matters more than feature count when building AI products
Soft SkillsUse lightweight, deterministic Markdown files as the backbone for reliable personal agents and workflows.
EngineeringHow to manage and preserve context when working with LLMs and agentic systems.
Soft SkillsPractical guidance on preserving context, choosing deterministic patterns, and using Markdown as an agent harness.
EngineeringPractical strategies to preserve context and improve results when developing with LLMs
Soft Skills