Research / Knowledge Work
Mostly Right is an AI-agent-powered platform for finding, building, and maintaining datasets for real-world prediction models. The page shows both a dataset browsing flow and a custom dataset builder, with agents handling source discovery, cleaning, joining, and ongoing updates.
The crawled page clearly presents a real AI-powered product with a specific use case: creating and maintaining research-ready datasets for predictive modeling. It includes visible product features, example datasets, an API, docs, pricing, and a clear workflow showing how the agents source, clean, combine, and keep data updated. That is enough evidence for a useful public listing.
The crawl does not show much about dataset breadth, which sources are supported beyond the example, or whether there are current public community datasets available yet. It also does not show pricing details, model compatibility, or a deeper product demo beyond the landing-page descriptions.
Last evaluated 3 days ago. Current rank #708. Down 3 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.
An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.
A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.
