Maersk Engineering: Translating SOPs and 100k Corrections for Agents
AI Engineer · youtube · 2026-08-30
Maersk's Dmitry Buykin shares engineering insights on deploying AI Agents in global shipping. The core challenge is translating human-readable screenshot SOPs into executable agent workflows (preconditions, decisions, backend calls).
Key Points:
- System is the Loop: The refining loop around the agent is the real system. Maersk spent 9 months making over 100,000 corrections; the procedure corpus outweighs runtime code 20:1.
- Accuracy is Earned: Accuracy comes from corrections, not upfront design. Heat maps turn traces into priorities.
- Context Matters: A single shipping step implies different things in different countries.
- Discovery vs. Production: Discovery needs agent freedom; production needs a cage to prevent dumb mistakes.
More from coding & agent
- Custom Agent panel supports adding archetypes and mid-session intervention — BLUECOW009 · 2026-08-30
- Karpathy's 2-Hour Lecture & Guide to Agent Loops and Graphs — JohnAlexander · 2026-08-30
- Uber's Software Factory: 70% of PRs Attributed to AI Agents — JohnAlexander · 2026-08-30
- Debate on AI Agent Communication: Is Silence More Efficient? — julianharris · 2026-08-30
- GLM-5.3 Released for Agentic Coding at 30% Lower Cost — markjeffrey · 2026-08-30
- Omarchy Multi-Agent Setup: Native MCP Mail and Board — BLUECOW009 · 2026-08-30