Mahal Systems DeepShop
Fits shopping research assistants. Borrow the fine-grained scoring of attributes, filters and sort order plus the easy / medium / hard query evolution.
What it asks the agent to do
- find products that satisfy several attributes, filters and a sort preference
- compare options across live shopping sites and report a result
What to borrow from it
grading designtaxonomy
Caveats
No code or license found; query count not stated; live sites drift; success rates under 35 percent at release.
Details
| Workloads | shopping, web browsing, research |
|---|---|
| Interaction | single turn |
| Environment | browser |
| End state checked | No |
| Tools | live shopping websites, search |
| Grading | programmatic check, llm judge |
| Size | Not published |
| Data | mixed |
| Personal data | none |
| License | unknown |
| Harness | none |
| Status | active |