Research / AI Agents
arXiv paper on Javo, a sales agent trained on commercial conversations and evaluated through public benchmarks plus a randomized field trial across 100 live websites.
The page clearly documents an AI sales agent and provides strong evidence of real-world evaluation: benchmark results, a randomized controlled trial, and comparison against both frontier models and human associates. It is useful for readers looking for AI agent research, sales automation systems, or applied AI benchmarking.
This is a paper abstract page, so it does not show a product site, code repository, or demo. The visible page also does not provide implementation details, access links for the agent, or a concise usage overview beyond the study description.
Last evaluated 6 days ago. Current rank #1651. Down 2 spots in the rankings.
Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.
An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.
A research article benchmarking bot detection systems against scripted browsers, stealth browsers, and modern AI browsing agents, with comparative results across five detection products.
An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.
