Semantic Caching: Skipping the Model Call When You've Already Answered the QuestionSemantic Caching7 min read·nagspidey.hashnode.devNov 10
Agent Loops Gone Wrong: Step Limits, Budgets, and Human Approval GatesAgent Loops Gone Wrong9 min read·nagspidey.hashnode.devNov 9
Tool Design for Agents: Writing Functions a Model Can Actually Use WellTool Design for Agents7 min read·nagspidey.hashnode.dev1ANov 6
LLM-as-a-Judge: Using One Model to Grade Another (and Where It Fools You)LLM-as-a-Judge8 min read·nagspidey.hashnode.dev12SNov 4
Hybrid Search and Reranking: Fixing Retrieval After Vector Search Falls ShortHybrid Search and Reranking8 min read·nagspidey.hashnode.dev15AANov 3