Hacker Newsnew | past | comments | ask | show | jobs | submit | think4coffee's commentslogin

Congrats on the launch! You mention that you're SOTA on benchmarks. Can you share your research, or share which benchmark you used?


thanks! we benchmark against all the major players (azure doc intelligence, aws textract, google doc ai, frontier llms, etc). we have some public news coming out soon on this front, but we have a very rigorous dataset using both public and synthetic data focusing on the hardest problems in the space (handwriting, tables, etc).


Are you guys Harry Potter fans? Curious how you came up with the name Reducto


Hahaha, a while ago (even before choosing this idea space) we said we would build "magical tools for developers" and Reducto was the name we landed on out of a long list of magic adjacent things


I’m trying to pick an OCR or document parsing tool, but the market’s noisy and hard to compare. If you’ve worked with any, I'd love your input.

1. What’s your primary use case or workflow involving document parsing or understanding?

2. Which tools or services are you currently using or have evaluated for document parsing or OCR?

3. What challenges or limitations have you run into with your current or past approach?

4. Why did you decide not to move forward with tools you’ve tried (if any)?

5. What are the top 2–3 things that matter most to you when choosing a tool like this?

6. What’s your typical monthly budget (or budget range) for document processing infrastructure?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: