Why all those steps? Why not just file + prompt to JSON directly?

Having the text (for now) is still pretty important for quality output. The vision models are quite good, but not a replacement for a quality OCR step. A combination of Text + Vision is compelling too.

Totally agree that this is becoming the standard "reference architecture" for this kind of pipeline. The only thing that complicates this a lot today is complex inputs. For simple 1-2 page PDFs what you describes works quite well out of the box but for 100+ page doc it starts to fall over in ways I described in another comment.

Are really large inputs solved at midship? If so, I'd consider that a differentiator (at least today). The demo's limited to 15pgs, and I don't see any marketing around long-context or complex inputs on the site.

I suspect this problem gets solved in the next iteration or two of commodity models. In the meantime, being smart about how the context gets divvied works ok.

I do like the UI you appear to have for citing information. Drawing the polygons around the data, and then where they appear in the PDF. Nice.