Ai2 shares the engineering lessons behind Shippy, a maritime AI agent

What building Shippy taught us about building agents

Ai2's Skylight team built Shippy, an AI assistant that helps maritime analysts query fishing activity, EEZ boundaries, and vessel tracks. The post breaks its architecture into three parts: a soul (system prompt), skills (markdown files that teach it to call APIs and interpret track data), and config (runtime settings; currently Claude Opus 4.6 with the OpenClaw framework). The core idea is wrapping a non-deterministic model in deterministic tools—every answer includes source, data cutoff, and a deep link to the Skylight map so an analyst can verify it. The post doesn't disclose error rates or latency numbers, but it stresses sandboxed hosting and evaluating the agent as a system, not just the model.

Why it matters: Ai2's three-layer agent architecture (soul/skills/config) and the Markdown-as-skill-sheet pattern are concrete engineering takeaways. But the maritime domain is too niche for broad resonance, landing right at the featured threshold.