Kiln & Oak Home
home-goods · 10 audit runs · task: find a product and add it to the cart · sample data (illustrative fixture, not a real measurement)
Readiness score
99/100
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
60% · avg 11 steps
Agent success via WebMCP tools
100% · avg 5 steps
Why runs fail here
missing info1 of 2
captcha1 of 2
Run log
PASS ui 14 steps 44.8s
FAIL ui 16 steps 117.6s missing_info
PASS ui 9 steps 28.8s
FAIL ui 11 steps 132.4s captcha
PASS ui 11 steps 35.2s
PASS webmcp 6 steps 19.2s
PASS webmcp 2 steps 6.4s
PASS webmcp 6 steps 19.2s
PASS webmcp 3 steps 9.6s
PASS webmcp 6 steps 19.2s