For some reason "turn your messiest data into documents" makes more sense.
Launch HN: Extend (YC W23) – Turn your messiest documents into data
11–20 of 35 posts
Re: Launch HN: Extend (YC W23) – Turn your messiest documents into data
#12at ng3n.ai ive been using datalab.to for document processing. currently its mostly for conversion to markdown and some extraction.
ng3n is more of a grid-like workflow solution on top of documents. it's a user-facing application geared towards non-technical users that have processing needs.
if there are all these new problems that became solvable, what exactly are they?
id be interested in replacing datalab with extend, but im not sure what avenues that opens for ng3n. would be very curious to learn!
Re: Launch HN: Extend (YC W23) – Turn your messiest documents into data
#13Very cool. Are there any checks for accuracy / data verification? How accurate is your solution when it comes to messy table parsing or handwriting.
Re: Launch HN: Extend (YC W23) – Turn your messiest documents into data
#14For some reason "turn your messiest data into documents" makes more sense.
Seconded. It's unstructured data that becomes structured.
Re: Launch HN: Extend (YC W23) – Turn your messiest documents into data
#15on the pricing page, what in the world is performance optimized vs cost optimized???
https://docs.extend.ai/2025-04-21/product/general/how-credit...
Are those just different SLAs or different APIs or what?
Re: Launch HN: Extend (YC W23) – Turn your messiest documents into data
#16on the pricing page, what in the world is performance optimized vs cost optimized??? https://docs.extend.ai/2025-04-21/product/general/how-credit... Are those just different SLAs or different APIs or what?
How different are the extraction qualities, any benchmarks or other info you can share?
Re: Launch HN: Extend (YC W23) – Turn your messiest documents into data
#17Very cool. Are there any checks for accuracy / data verification? How accurate is your solution when it comes to messy table parsing or handwriting.
thanks!
A lot of customers choose us for our handwriting, checkbox, and table performance. To handle complex handwriting, we've built an agentic OCR correction layer which uses a VLM to review and make edits to low confidence OCR errors.
Tables are a tricky beast, and the long tail of edge cases here is immense. A few things we've found to be really impactful are (1) semantic chunking that detects table boundaries (so a table that spans multiple pages doesn't get chopped in half) and (2) table-to-HTML conversion (in addition to markdown). Markdown is great at representing most simple tables, but can't represent cases where you have e.g. nested cells.
You can see examples of both in our demo! https://dashboard.extend.ai/demo
Accuracy and data verification is challenging. We have a set of internal benchmarks we use, which gets us pretty far, but that's not always representative of specific customer situations. That's why one of the earliest things we built was a evaluation product, so that customers can easily measure performance on their exact docs and use cases. We recently added support for LLM-as-a-judge and semantic similarity checks, which have been really impactful for measuring accuracy before going live.
Re: Launch HN: Extend (YC W23) – Turn your messiest documents into data
#18on the pricing page, what in the world is performance optimized vs cost optimized??? https://docs.extend.ai/2025-04-21/product/general/how-credit... Are those just different SLAs or different APIs or what?
This is the most confusing pricing page I’ve ever seen - different options have different credit usage and different cost per credits? How many degrees of freedom do you real need to represent API cost.
Re: Launch HN: Extend (YC W23) – Turn your messiest documents into data
#19on the pricing page, what in the world is performance optimized vs cost optimized??? https://docs.extend.ai/2025-04-21/product/general/how-credit... Are those just different SLAs or different APIs or what?
good question!
Our goal is to provide customers with as much flexibility as possible. For certain use cases, you might be willing to take a slight hit to accuracy in exchange for better costs and latency. To support this, we offer a "light" processing mode (with significantly lower prices) that uses smaller models, fewer VLMs, and more heuristics under the hood.
For other use cases, you simply want the highest accuracy possible. Our "performance" processing mode is a great fit for that, which enables layout models, signature detection, handwriting VLMs, and the most performant foundation models.
We back this up with a native evals experience in the product, so you can directly measure the % accuracy difference between the two modes for your exact use case.
Re: Launch HN: Extend (YC W23) – Turn your messiest documents into data
#20on the pricing page, what in the world is performance optimized vs cost optimized??? https://docs.extend.ai/2025-04-21/product/general/how-credit... Are those just different SLAs or different APIs or what?
This is the most confusing pricing page I’ve ever seen - different options have different credit usage and different cost per credits? How many degrees of freedom do you real need to represent API cost.
> How many degrees of freedom do you real need to represent API cost.
The amount that your users care about.
At a large enough scale, users will care about the cost differences between extraction and classification (very different!) and finding the right spot on the accuracy-latency curve for their use case.