Practical AI engineering by Slava Dubrov

The parts of AI systems that survive production

Agent runtimes, memory, security, retrieval, evaluation, LLM infrastructure — written up the way I’d hand them to the next engineer on the team.

Read the agentic stack series Browse all articles (33)

Byte, the Edge of Context beaver

Engineering the Agentic Stack

In order. Start at the loop.
  1. 01 AI Agent Reasoning Loops: ReAct, ReWOO, Plan-and-Execute 11 min
  2. 02 AI Agent Memory Architecture: Checkpoints and Vector Stores 33 min
  3. 03 AI Agent Tool Use: MCP, CLI, Skills, and Code Execution 18 min
  4. 04 AI Agent Security: Permissions, Sandboxes, and MCP Threats 35 min
  5. 05 Long-Running AI Agent Runtime: Sessions and Checkpoints 38 min
  6. 06 Harness Engineering for AI Agents: Designing Control Loops 24 min