Ethan Cohen, We discussed OCR capability with our Tech team, and turns out that OCR pipelines are not yet optimised for cost, quality and most importantly -- time efficiency. We're aware that Claude has added OCR recently, but we're still figuring out how to implement it in the best way possible. Unfortunately, it'd have to wait for a while. We'll let this thread know when we get headway. Thanks!

Hey team - do we have a timeline to release on this one? Feel like we're getting a lot of likes but haven't seen any movement.

It would be useful to be able to say "do XYZ based on the tex tin the image", for example.