0/6 major aerospace documentation portals are AI Agent-ready
None of six major aerospace documentation portals are "AI agent-ready," according to a student-built scoring engine called AeroScore. The best score was ICAO with 69/100; no site had an llms.txt or supported URL variants. The author warns this hinders potential productivity gains from AI in aerospace.
Background
- An incoming aerospace engineering undergrad built AeroScore, which grades documentation portals on how easily LLM-based "AI agents" can parse them. The grading is based on AFDocs, an open-source checklist for agent-friendly documentation.
- Six major aerospace portals were scored: none are "agent-ready." The top score (ICAO, the UN civil aviation body) got 69/100. None had an `llms.txt` file (a standard telling AI crawlers how to handle the site) or supported URL variants.
- "AI agent-ready" means a site's content is structured so AI tools can extract data without human-like clicking. Many tech fields already do this.
- Aerospace remains PDF-heavy; PDFs are harder for agents to parse than structured web pages. The post argues this slows down engineering, safety analysis, and compliance work in the field.