Query your CSVs in Claude, next to the rest of your data
Upload a CSV to Contextflo and query it in Claude with real SQL, on its own or alongside your warehouse data. How it differs from a chat upload, and how it works under the hood.
Not every team has a data warehouse. Even fewer have a data team. Most just have a pile of CSVs, vendor exports, finance sheets, ops trackers, getting passed around and picked apart by hand.
The problem isn't any one file. It's that the answer you want usually needs the CSV and the data you already have, together. And a CSV in your inbox doesn't talk to your warehouse.
So we added CSV upload. Drop in a file, and it becomes a table you can query in Claude, on its own or next to everything else you've connected.
What it looks like
Say you run an e-commerce brand. Your orders and revenue are in your warehouse. Your product costs are in a spreadsheet. They never made it in, because costs come from POs and supplier negotiations, not your checkout.
So you can see revenue by product. You can't see profit. The cost half is stuck in a CSV.
Upload the cost sheet and ask Claude: which products are most profitable after cost? Claude pulls revenue from your warehouse, costs from the CSV, and gives you profit and margin by product. Usually the surprise is that your best seller isn't your best earner.
And since the CSV lives in Contextflo, not one person's chat, the whole team can ask the same thing.
How is this different from uploading to a chat?
You can already drop a CSV into Claude and ask about it. For a quick, one-off file, do that. It's free and simpler.
Two things you can't do there:
- Query it next to your other data. In a chat, the CSV is trapped on its own. Here it sits next to your warehouse, so Claude can pull from both in one question.
- Share it. A chat upload is yours, for that one conversation. Here it's a table anyone on your team can query, any time.
One-off, personal, standalone: use the chat. Stays around, shared, needs your other data: use this.
Under the hood
Your files go into an S3 bucket only your org can access. Nothing shared, nothing public.
At query time, we load the file into DuckDB and Claude runs real SQL against it through MCP. So “average order value by region” is an actual GROUP BY, not the model eyeballing a wall of text.
For a question that spans the CSV and your warehouse, Claude queries each one separately and combines the results. Two queries, one answer.
Prefer to keep your files in your own storage? You can bring your own bucket.
Free for one user and one data source. Upload a CSV and ask a question.