RAG

• 
  Agents

  From RAG to Agentic Memory, a Working Blueprint

  Replace static RAG with a memory-first agent. A working blueprint for episodic, semantic, and working memory.

  Marco Kotrotsos·5 May 2026·6 min read
• 
  RAG

  Hybrid Search in 90 Minutes Is the Biggest RAG Fix

  Industry analysis shows 73% of RAG failures come from retrieval, not generation. Here is the 90-minute fix.

  Marco Kotrotsos·5 May 2026·7 min read
• 
  RAG

  Build a 1M Context Document Copilot with DeepSeek V4 Pro

  DeepSeek V4 jumped from 128k to 1M tokens. Long context is now cheap enough to actually use, here is when to and when not to.

  Marco Kotrotsos·5 May 2026·6 min read