dsbuddy
Try it free
AI dataset analysis

Drop a file.
Walk out with answers.

Upload a spreadsheet and dsbuddy profiles it, models it, and tells you what actually matters — in plain English, in under a minute.

Try it free

200+ statistics · 3 models on a held-out test set · one verdict you can act on

customer_churn.csv
Live

Feature relationships

Rows analyzed

7,043

Best model

86%

Model comparison

Logistic Reg.78%
Random Forest84%
Grad. Boosting86%

Top finding

High

contract_end_date is 94% correlated with the outcome — likely leakage.

What happens after you hit upload

From raw file to real understanding

01

Upload dataset

Drag a CSV, XLSX, or Parquet in. That's the only manual step in the whole pipeline.

customer_churn.csv

100%
02

Validation

Before anything runs, we check structure — types, headers, encoding, duplicate columns.

Headers detected
Types inferred
Encoding: UTF-8
0 duplicate columns
03

AI analysis

Claude reads every column and tags what it actually means — currency, category, identifier, date.

Reading tenure_months, monthly_charges, contract_type…

04

Data flow

Your data streams through profiling, correlation, and modeling stages — live, not a black box.

Scan
Profile
Graph
05

Processing nodes

Three models train in parallel, each scored on a 20% test set they never saw during training.

Logistic Reg.78%
Random Forest84%
Grad. Boosting86%
06

Insights

Claude reasons over the full profile and ranks what actually matters — and what to fix first.

Highcontract_end_date looks like leakage
Med76/24 class imbalance on target
Lowmonthly_charges is 12% missing
07

Interactive dashboards

Everything lands in one dashboard — charts, risk flags, and a place to ask follow-up questions.

Try it now

Fresh datasets, ready to go

Questions

Good to know

dsbuddy

Built for people who’d rather understand their data than wrangle it.