Understands any spreadsheet
Drop in the CSV or Excel file you already have. Plotwell reads the header row and figures out which columns are dates, categories and numbers. No template to pick, no field mapping to fill in.
Product
A spreadsheet in, a dashboard and the takeaways out
Upload a CSV or Excel file. Plotwell reads the columns, picks the charts that fit, builds a clean dashboard and writes the plain-language takeaways. The whole thing takes about twenty seconds.
What it does
Eight things, none of them decoration
Picks the charts that fit
Not every column needs a chart, and not every chart fits every column. Plotwell selects the views that actually answer a question, skips the ones that would just fill space, and lays them out in a clean dashboard.
Plain-language takeaways
Next to each chart, Plotwell writes what changed, what looks off and what to look at next. Two to four sentences, using the numbers from your data. No jargon, no hedging.
Outlier and trend flags
When one row is far outside the others, or when a line has been moving in one direction for three periods, Plotwell names it. You see the flag in the takeaway, not in a side panel you have to click into.
Export and share
On Pro and Team, export the dashboard as an image or download the cleaned data as a CSV. A share link gives anyone read-only access to the same view, with no login needed.
Dashboard history
Every dashboard you build is saved. Come back to last month's run and compare it to this month's without uploading the old file again. The history panel shows the file name and the date.
Files up to 50,000 rows
On Pro and Team, files up to 50,000 rows in a single upload. Plotwell sends a compact profile of your columns to the model, not every cell, so large files stay fast and your raw data is not sent unnecessarily.
Your data stays yours
Your file is processed to build your dashboard and for nothing else. It is sent to a model provider under agreements that prohibit training on it and never sold. Delete any dashboard or your whole account from Settings at any time.
See it on real data
A real dashboard, built from real rows
Every bar below is a sum of the sample rows. The takeaways are generated from those numbers. Nothing here is a picture of a dashboard.
Dashboard
Online store, 2024
A year of revenue for a small online store, split across four channels. Revenue is up over the year, orders track it, and the refund rate is worth watching.
48 rows · 6 columnsstore-2024.csvbuilt with gpt-4.1-mini
Total revenue
$0
+18% first to last
Orders
0
Revenue by month
Summed across every channel.
Revenue by channel
Which channel brings the money in.
Refund rate by month
Mean refund rate. Worth watching.
Revenue share by channel
- Organic40%
- Paid Se32%
- Email18%
- Referral10%
Outliers
Ad Spend
14,125
At 2024-09, 262% above the usual range.
The honest part
Describes, never fabricates
Every chart is built by aggregating your real rows in code. The model chooses which columns to chart and writes the takeaways. Any takeaway that cites a figure Plotwell cannot read from your data is dropped before you see it.
Plotwell does not invent numbers. If a column is empty, it says so. If the data is too sparse to show a trend, it does not show one.
Charts from code
Every bar, line and table is the output of an aggregation query against your rows. The model never draws numbers from memory or training data.
Takeaways verified
Before a takeaway reaches you, any figure in it is checked against the computed output. A number that does not appear in the data is removed.
Sparse data flagged
If a column has too few values to show a meaningful chart, Plotwell names the gap instead of guessing. Thin data is marked thin.
Model-agnostic
Plotwell runs on whichever model fits the step. It is not tied to one lab or one provider, and the routing table is published openly on the How the AI works page.
What it reads
The spreadsheets founders and operators actually keep
If it has a header row and at least a couple of rows of data, Plotwell reads it. Any CSV, TSV or Excel file, the kind you already export from your tools.
- Sales exports and revenue by period
- Ad spend and campaign performance
- Survey responses and NPS results
- Order and fulfillment logs
- Inventory and stock levels
- Churn and retention data
- Payroll and headcount records
- Pipeline and deal stage reports
Try it on the spreadsheet you already have
Four dashboards a month are free. No card, no setup. If it does not tell you something useful about your own numbers, you have lost twenty seconds.