Monsoon Threads
fashion · 5 audit runs · task: find a product and add it to the cart · sample data (illustrative fixture, not a real measurement)
Readiness score
19/100
70% task success · 15% WebMCP tool surface · 15% efficiency (steps to complete). Full rubric in the open methodology.
The WebMCP delta
Agent success via raw UI
20% · avg 15 steps
Agent success via WebMCP tools
No WebMCP tools exposed — this is the opportunity.
Why runs fail here
captcha2 of 4
timeout1 of 4
popup interference1 of 4
Run log
PASS ui 15 steps 48.0s
FAIL ui 17 steps 109.2s captcha
FAIL ui 15 steps 100.0s captcha
FAIL ui 21 steps 131.7s timeout
FAIL ui 18 steps 117.4s popup_interference