Agent: DS-Star

Data Science Agent for Multi-File Analysis with DS-Star

Best for: data science agent

Data-science runtime optimized for iterative coding and streamed analysis in the co-scientist loop.

Analyze messy, multi-file datasets and turn open-ended questions into reproducible reports.

DS-Star is a data-science agent designed for real-world analysis tasks that involve messy, multi-file datasets and open-ended questions. It can work across different file formats, combine information from multiple sources, and produce full research-style reports instead of only short answers. In evaluations, DS-Star performs especially well on harder tasks that require multi-file reasoning and code-based analysis.

Analyze files with DS-Star Run example prompt

Data is encrypted at rest. Attachments you upload into the agent workspace are deleted after a period of time, and we will notify you when that happens.
We recommend not uploading personally identifiable information or sensitive data.

20minds Co-Scientist workspace showing agent output, code, and controls

Example prompts you can run

QUESTION

🚢 Using the /app/custom_data/titanic.csv dataset, write a short report for a general audience with: 1) overall survival rate, 2) survival rate by sex, 3) survival rate by passenger class (Pclass)

EXPECTED ANSWER

Overall survival: 38.38% (342/891). By sex: female 74.20% (233/314), male 18.89% (109/577). By class: 1st 62.96% (136/216), 2nd 47.28% (87/184), 3rd 24.24% (119/491).

FILEStitanic.csv

Details

License: https://github.com/JulesLscx/DS-Star
Citation: Nam et al. (2025). DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries. arXiv preprint.
Models: gemini-3-flash-preview, gemini-2.5-flash

Running this for a team? Book a demo or contact us.