MIT Prof Built an AI Playbook That Audits Academic Websites and Simulates Visitors
soumitrashukla9 · x · 2026-10-23
MIT Sloan professor John J. Horton released a "playbook" for AI-reviewing academic websites: it checks navigation, accessibility, organization, and link freshness, and simulates potential visitors to see whether they can accomplish their goals. Running it on his own site surfaced real issues — duplicated year displays in awards/grants, declined talk invitations containing personal health details, and a page-title inconsistency.
The full report (produced via Expected Parrot) includes screenshot-level visual inspection across desktop viewports, and he shared a self-serve entry so anyone can paste their URL and run the same review.
More from coding & agent
- Using councils of models: multi-model voting rounds to converge on better outputs — ykdojo · 2026-10-23
- Railway and OpenCode breached as attackers hunt for your AI API keys — thursdai_pod · 2026-10-23
- Dev launches swap/bridge MCP server comparing DEX aggregator quotes across 12 chains — TakesThisSeriously · 2026-10-23
- Open-source browser agent Jev cuts median task time from 9.45s to 7.09s — abhishek__AI · 2026-10-23
- Onyx: open-source enterprise AI chat and search platform with 32.9k GitHub stars — adnan_hashmi · 2026-10-23
- Hermes Agent hits 395 real user stories; one IT staffer runs 80% of a 165-person company's work — NousResearch · 2026-10-23