Incredibly excited to share more about Reducto Studio today. We started by building the most accurate APIs, and are now building a platform to help everyone use them. Studio is a toolkit for building, evaluating, and deploying production-ready document processing pipelines.

You can try it yourself at We're also now live on product hunt and would love any questions or feedback there:

With Studio you can: - Drop an entire file set and get per-field and per-document accuracy scores against your evaluation data. - Let Studio build and refine your extraction schema for you, automatically optimizing in between runs. - Save your runs for comparison, and invite non-engineering teammates to collaborate as well.

Super excited by the feedback we've gotten from early customers and excited to share a wave of updates for this platform in the coming few weeks!

really great stuff, feels intuitive to use

Thanks Anson!

Really cool! How large of a document can you set parsing rules for?

You can build pipelines for docs with thousands of pages :)

Does it work in Minecraft?

You should make it work in Minecraft, that's the big missing feature

🔥🔥

🫡