Runs

every end-to-end agent run, scored against its engagement's golden reference

kingsway

modelling · azure_openai · 2026-07-12

0% planted DQ found · 0 keys verified · 0 mapping files

kingsway

mappings rendered

modelling · azure_openai · 2026-07-12

29% planted DQ found · 8 keys verified · 14 mapping files

kingsway

discovery · azure_openai · 2026-07-12

0% golden match · 6/6 traps dodged

kingsway

discovery · azure_openai · 2026-07-10

0% golden match · 6/6 traps dodged