I built IntentLens to make metric definitions visible before generating charts

A chart can look right while answering the wrong question.

For example, imagine two groups:

• Group A: 10 conversions from 100 visits → 10%.
• Group B: 5 conversions from 10 visits → 50%.

The overall conversion rate is 15 / 110 ≈ 13.64%.
The average of the two group rates is 30%.

Both calculations are valid, but they answer different questions. I wanted that choice to be visible before a chart is generated.

What I’m building

IntentLens is a local Excel/CSV visualization workbench.

The workflow is:

Import data → Describe the question → Review a plan → Compute → Refine → Export

Before execution, you can inspect grouping, aggregation, ratio definitions and missing-value handling. The full application also supports chart revisions and reproducible exports.

Models propose declarative analysis plans rather than arbitrary Python or JavaScript to execute. The application validates those plans and computes results from a data snapshot.

Try the English interactive sample

Open the sample

No installation, signup or API key is required.

Try one small task:

1. Select the conversion-rate question.
2. Compare overall conversion with average monthly conversion.
3. Generate a chart.
4. Change its title or ordering.
5. Download a result.

The public sample uses fixed synthetic data and deterministic rules. It does not call AI or accept file uploads.

The two-group example above explains the concept; it is separate from the sample’s 12-record dataset.

What the full local application adds

The full workbench supports your own Excel/CSV files, conversations with a configured model, multiple chart engines and revision history.

I also recorded an English walkthrough of the actual local workflow: uploading a synthetic CSV, entering a question, receiving a plan from DeepSeek and generating a chart. The computed regional totals were checked against the input data.

The project is still a development version intended for trusted local, single-user use. Model-assisted planning requires an API key and sends field metadata and statistics to the configured provider.

Source code and installation instructions

The feedback I need

I’m trying to understand whether the confirmation step earns its place in a real reporting workflow.

If you regularly work with spreadsheets:

• For your last report, would reviewing the metric definition have prevented a mistake or added friction?
• Where did you get stuck in the sample?
• What would you use instead, and what does that workflow do better?

I’m also looking for five people with recurring reporting tasks to try the full application using public or sanitized data.

Comments and concrete criticism are welcome. No star required.