AI Agents
Memory/Tools/Orchestration/Evaluation
How agents reason, remember, use tools, coordinate tasks, and become useful beyond a single prompt.
What turns a language model from a prompt-response system into something capable of pursuing a goal over time?
What I'm looking at
Memory
Short-term context, long-term memory, retrieval strategies, and deciding what is actually worth remembering.
Tools
How agents interact with external systems safely and reliably instead of trying to solve everything inside the model.
Orchestration
Planning, task decomposition, delegation, workflows, and deciding when agentic behavior is actually useful.
Evaluation
Measuring whether an agent reliably achieves useful outcomes instead of merely producing convincing responses.
Related
Personal Knowledge Agent
A personal RAG system for retrieving, connecting, and reasoning over my own knowledge.
Architecture Agent
An AI assistant for exploring architecture options, trade-offs, and engineering decisions.