Learning
5 articles about learning.
An AI Assistant That Actually Learns How You Work Over Time
Most AI assistants reset every session. A persistent knowledge graph that indexes contacts, habits, and app usage anticipates your needs after two weeks.
Learning Path for Local LLMs - From Ollama to Desktop Agents
A practical learning path for running local LLMs: start with Ollama basics, learn prompting, understand quantization, build workflows, then automate your desktop.
Skip the AI Books and Just Build Something
The best way to learn AI agents is to build one. Reading about agent architecture for a month when you could have built 3 agents in that time is a trap.
Skill Templates vs Agents That Learn - Two Approaches to Desktop AI
Skill templates give structure for common tasks. But agents that learn your habits over time build their own understanding of how you work.
Traces of Successful Workflows Are the Most Valuable Context for AI Agents
Why feeding your AI agent real workflow traces produces better results than documentation alone, and how to capture them.