AI News HubLIVE
In-site rewrite2 min read

Show HN: TamedTable – AI ETL in Natural Language

TamedTable is an AI ETL tool that lets you transform tabular data using natural language instead of formulas or code. It supports CSV, JSONL, Parquet, and Arrow files, and provides clean, enrich, classify, validate, and language-processing operations. Every change can be undone, saved as a replayable recipe, or exported as a Python script. The benchmark shows 96.7% agreement with hand-checked labels at about $0.15 per 1,000 rows classified.

SourceHacker News AIAuthor: ZeljkoS

Talk to your data.

Load tabular data, say what you want, and watch it happen. AI ETL: no formulas, no code.

Open Web App View on GitHub

No API key? Take a guided tour: it replays real sessions, free.

TamedTable

> normalize the phone numbers

NamePhoneCountry

John D. Doe(200) 555-1234+12005551234USA

Anna Müller+49 555 6789+495556789Germany

张三+86 555 1234+865551234China

Every common data job, in natural language

Transform with context

The AI understands context, so it cleans, enriches, classifies, and validates — things no formula can.

See everything

See changes as they happen. Nothing is hidden: TamedTable is source-available, and runs on your own API keys.

Reuse and automate

Every change saves as steps you replay on new data, or export as a Python script. Runs in browser and CLI.

Read many formats

Open CSV, JSONL, Parquet, and Arrow files — local, from a URL, or a bundled sample.

How it works

1

Add API keys

Just the first time you start the app.

2

Open a file

CSV, JSONL, Parquet, or Arrow. Local or from a URL.

3

Say what you want

Works in any language: English, Chinese, etc.

4

Watch changes

Dislike changes? Undo anything.

5

Automate

You made a recipe; replay it on new data.

Lazy AI execution

Preview for cents, run for real when you're sure. AI steps fill the page you are looking at; the rest waits until you ask.

Show me →

Clean up

Fix messy fields the way a person would. The AI reads each row's context before deciding.

Show me →

Enrich & extract

Add what isn't there yet. The model fills the gaps and pulls structure out of free text.

Show me →

Classify

Sort rows by what they mean. The AI reads what each row is about.

Show me →

Validate

Catch the wrong-looking rows before anyone else does.

Show me →

Process language

Summarize, translate, and classify any language.

Show me →

Be exact

The everyday spreadsheet jobs are still here; deterministic and repeatable.

Show me →

Load, save & reuse

Your work is yours to keep. Load from anywhere, save the data or the recipe, undo anything.

Trustworthy by design

A repeatable recipe

Each request becomes a small spec you can read. Deterministic steps run in a real SQL engine, and the same recipe replays on next month's file.

Undo anything

Every change lands in the history. Step back one change or all of them; the original file on your disk is never touched.

Leave anytime

Export any recipe as a plain Python script and run it without TamedTable. Your data stays in open formats; there is no lock-in to defend.

Tested & benchmarked

CI replays 606 test scenarios on every commit. In our benchmark, the default model matched hand-checked labels 96.7% of the time, at $0.15 per 1,000 rows classified.

Try it in two minutes

Source-available. Runs on your own API key, or take the guided tour without one.

Open the web app View on GitHub