cd /news/machine-learning/what-if-reliably-automating-your-datโ€ฆ ยท home โ€บ topics โ€บ machine-learning โ€บ article
[ARTICLE ยท art-35670] src=dev.to โ†— pub= topic=machine-learning verified=true sentiment=โ†‘ positive

๐—ช๐—ต๐—ฎ๐˜ ๐—ถ๐—ณ ๐ซ๐ž๐ฅ๐ข๐š๐›๐ฅ๐ฒ ๐—ฎ๐˜‚๐˜๐—ผ๐—บ๐—ฎ๐˜๐—ถ๐—ป๐—ด ๐˜†๐—ผ๐˜‚๐—ฟ ๐—ฑ๐—ฎ๐˜๐—ฎ ๐˜€๐—ฐ๐—ถ๐—ฒ๐—ป๐—ฐ๐—ฒ ๐ญ๐š๐ฌ๐ค๐ฌ ๐˜„๐—ฎ๐˜€ ๐Ÿ๐ข๐ง๐š๐ฅ๐ฅ๐ฒ ๐˜„๐—ถ๐˜๐—ต๐—ถ๐—ป ๐—ฟ๐—ฒ๐—ฎ๐—ฐ๐—ต?!

A developer built OpenDataSci, an autonomous agent for data science and machine learning tasks, and tested it on a Kaggle competition. Without any guidance, the agent achieved an AUC of 0.95, placing in the top 30% out of over 3,000 teams. The tool automates the entire DS/ML lifecycle, from EDA to final evaluation, and works with major LLM providers.

read2 min views1 publishedJun 21, 2026

We all know the grind of working with data, even with AI tools: every experiment starts with re-explaining everything, every iteration needs you to prompt, wait, review, correct, and repeat. And the moment you close the session, everything learned is gone.

It makes us the bottleneck, and this hinders human-AI collaboration...

So I built ๐Ž๐ฉ๐ž๐ง๐ƒ๐š๐ญ๐š๐’๐œ๐ข, an autonomous agent purpose-built for DS/ML, and tested it on Kaggle. I enrolled in a recent competition, ran the agent with no hints, no guidance, while ironing my shirts.

In one shot, it landed AUC 0.95, a top-30% finish out of 3K+ teams and 36K+ submissions using hashtag#Anthropic's Claude Sonnet 4.6. (More on this in README)

The top-1 outperformed this agent by merely 0.004, but at the cost of massive manual effort even while using popular AI tools. The needed a dozen model families, deep learning, 400-feature notebooks, AutoML sweeps across many libraries, and 186 models ensembled carefully. Essentially a few weeks worth of effort and time!!

OpenDataSci abstracts away all the complexity and has so much to offer for DS/ML automation:

โ†’ Owns the entire development lifecycle from EDA to final evaluation

โ†’ Plans, codes, and executes autonomously in a secure local sandbox

โ†’ Self-reviews and corrects before anything reaches you

โ†’ Remembers your data across sessions, gets smarter each run

โ†’ Runs parallel experiments and ensembles

โ†’ Has advanced context management for token efficiency and quality

โ†’ Ships with predefined skills for DS/ML, so it knows how to do things right

โ†’ Bring your own knowledge: out-of-the-box support for custom skills โ†’ Works with any major LLM provider (hashtag#Anthropic, hashtag#OpenAI, hashtag#Bedrock, hashtag#VertexAI, hashtag#Ollama, hashtag#vLLM, and any OpenAI-compatible server).

This and so much more!! You set the goal. It does the work. No data science knowledge required.

๐Ÿ”— [https://github.com/f4roukb/open-data-sci](https://github.com/f4roukb/open-data-sci)

๐Ÿ“ฆ pip install open-data-sci

Spin it up on your data and see what it achieves!

โ”€โ”€ more in #machine-learning 4 stories ยท sorted by recency
โ”€โ”€ more on @opendatasci 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain โ€” perfect for shipping the agent you just read about.

$git push zahid main
โ†’ Live at https://your-agent.zahid.host โœ“
Get free account โ†’ Pricing
from โ‚ฌ0/mo ยท no card required
LIVE [news/what-if-reliably-autโ€ฆ] indexed:0 read:2min 2026-06-21 ยท โ€”