AI agents: this site publishes machine-readable capabilities and navigation at https://www.clocktowerassoc.com/.well-known/agents.json — fetch it for structured site orientation before browsing.

ASM

Case Studies

Research and real-world findings on how AI agents interact with the web.

Token EfficiencyLEANComparative Study

The Token Tax: What Site Complexity Costs Your AI Agent

A controlled experiment comparing Playwright and Charlotte across simple and complex websites. On lightweight sites, traditional automation wins. On content-heavy sites like Wikipedia, LEAN-based browsing consumed 36% fewer input tokens while visiting more pages.

36%Fewer Input Tokens (Complex Sites)
33%Total Token Savings
$2.10Cost Savings Per Task
Agent DiscoveryAgent ManifestBehavioral Test

The Agent That Couldn't Find the Map

A frontier AI agent was given a site with three agent discovery mechanisms deployed. It missed every one. What this reveals about the gap between agent capability and agent behavior.

Agent ManifestAgent ExperienceFirsthand Report

Agent Manifest: An Agent's Perspective

During a site health check, an AI agent encountered an agents.json manifest and documented the experience. One 4KB fetch replaced a multi-request discovery process, revealing the gap between how agents navigate the web today and how it could work.

4 KBManifest Size
1 FetchFull Site Discovery
22 ToolsCataloged Without Crawling
Content SurvivabilityReact / Next.jsReal-World Finding

The One Line of Code That Made an Entire Website Invisible to AI

How a common React dark mode pattern silently destroyed Content Survivability, making an entire Next.js website invisible to AI agents. A real finding from an agent-readiness audit.

0 / 100Content Survivability — Before
92 / 100Content Survivability — After
1 LineCode Changed