Charts of your data, from a sentence
Drop in a spreadsheet or connect a database, then ask for what you want to see. It finds the columns, joins them, shapes them and draws the chart — every time, never an apology.
Ask one question now without an account. Sign in for 10 free charts a month — no card, and the sample data is already loaded.
How it works
It always gets you a chart
Most data assistants hand back a paragraph explaining why they could not help. This one draws something every time. If two tables share no values it drops the join and charts what is left. If its own shaping code fails it charts the cleaned data instead. If the question is vague it picks the most useful cut and names the one it rejected. You get a figure, plus a plain note about anything it had to approximate.
orders joined to regions — 3 columns are enough to answer this.
region_id → id, 98% value overlap. Row count unchanged, so the key is unique.
Monthly totals per region, sorted by date so the line reads left to right.
Time on x, one line per region. A bar chart would hide the crossover in August.
Palette, spacing and labels applied. 0 issues found.
Chart quality
Charts that do not mislead
The rules are enforced in code, not left to taste. Every chart is audited against them before you see it — including the three below.
What is enforced
- Hues are assigned in fixed order and never cycled — a ninth series folds into Other rather than reusing a colour.
- Scatter and map forms cap at three series, because past that no palette stays colour-blind safe.
- Never two y-scales on one plot. Mismatched measures get their own chart instead of a fake correlation.
- Light and dark are separately validated, not flipped.
- Every finished chart is re-audited; anything that slips through is reported beside it.
Worked examples
13 datasets, already loaded, already answered
Every account starts with these. Each one has a page with its schema, its rows, and the charts the pipeline drew from them — with the reasoning behind every choice one click away. No account needed to read them.
Your data
Whatever the data lives in, it can chart it
Drag in a CSV, Excel file or Parquet extract and ask a question thirty seconds later. Or connect the warehouse and leave the rows where they are — everything is read-only, and generated SQL is checked before it ever reaches a driver.
After the first chart
The chart is a starting point, not a screenshot
Change it for free
Swap the axes, the chart type, the grouping or the aggregation by hand and it redraws — no model call, no credit spent. Or say what you want changed in words and let the edit stage apply it.
Real Python underneath
The shaping runs in a sandboxed interpreter with pandas, polars, numpy, scipy, scikit-learn and statsmodels — so “fit a trend and forecast the next quarter” is a question, not a feature request. The code is shown and editable.
A real SQL editor
For when you already know the query. Schema-aware completions answer instantly without waiting on a model, plus generated SQL, per-source suggested questions and saved history.
Take it with you
SVG, PNG or CSV; pin it to a
dashboard with a share link that needs no account; export the whole run as
a Jupyter .ipynb or a marimo notebook — both run here as
well as on your laptop; or call the same pipeline over HTTP.
Get started
Chart something you actually care about
Ask one question now without an account. Sign in for 10 free charts a month — no card, and the sample data is already loaded.
Open twoHelixes