Workflows are the most common, there's a pipeline like processing loan documents before data gets loaded to the next step or translating user comments before being stored in the database.
Agents are where you have a chat based system or a brain of sorts that calls many tools to achieve a user goal. The model doing this is a lot better at non deterministic task which then delegates to Interfaze for specific deterministic actions like OCR, Web extract then consumes that data. That's the article you referenced :)
It can, you could try prompting the model to use object detection vision and text extraction, we realized when we purely extract text it does amazing at word/sentence level bounds since the text acts as the anchor. However, when you treat it as a object detection problem, it sees that chunk of text as a segment allowing you the extract it as one column bound. Give that a try.
Not directly, LAMs tend to be focused a lot on tool calling or trained for a set of specific action for example in the robotics field. Good tool calling might be a good by product of Interfaze but wasn't specifically trained for that use case.
The focus has been for deterministic outputs that require high accuracy. In situations where there is "one right answer"
It wasn't designed to do well on MMMLU, it's a general model designed for deterministic task like OCR, object detection, STT and more and a by product of that is great language abilities. It still has a transformer backbone giving great language skills while being good at other stuff.
For sure there a tons of OCR bounding models and tons of other models like SAM 3 for segmentation.
Interfaze is a more powerful version of them combined into a single model, you can run multi turn tasks like extract all the text and object from this document then translate or generate a report.
It's like getting the best of both worlds from pure DNN/CNN models like Paddle and the flexibility and nuace of an LLM while outperforming both in accuracy.
The other way round, task specific DNNs adapted to share the same vector space as omni-transformers with generalized vision, audio encoders.
E.g. For an OCR task, the first pass will be handled by the CNN, converted to shared tokens which the transformer can consume, correct any issues if needed and a decoder that can handle both the DNN and transformer output.
Google Cloud Vision AI is a specialized model built on CNNs frameworks which is part of the Interfaze architecture which is an hybrid so you get best of both worlds. Google cloud vision was pretty far behind other specalized models like PaddleOCR etc anyways so if you're looking for a pure CNN, check them out.
You can find the explanation and the comparison in the article, which we benchmarked pure CNN models, pure LLM models and a hybrid architecture like ours.
Yup run task mode runs a much smaller part of the model when can drop quality of scans. The issue with run task we have to figure out is how much of the model is needed just for OCR and how to activate the right parts. A lot more improvements coming here with the same cost reduction.
I'd be happy to test it against your sample and see how we can get good results at a lower per page cost. Feel free to email me [email protected]
It isn't on our roadmap right now since in most cases it should work out of the box and if it doesn't we'll work with you to train that into the model generally.
However, if we see enough people who has something super niche that our model can't handle, we might start considering a fine tuning service
At JigsawStack, we’re building specialized small models that automate complex backend tasks like OCR, web scraping, classification, data extraction, and more. We power thousands of developers and process billions of tokens every month.
We’re hiring our first Founding GTM, someone who wants to architect the entire GTM engine, experiment aggressively, and push the boundaries of AI growth.
You’ll own automation, outbound systems, GTM tooling, growth experiments, and the workflows that expand JigsawStack’s reach. This is a growth role where you’ll build pipelines, write scripts, automate everything possible, and systematically scale distribution.
As an early team member, you’ll work directly with the founders, run high-velocity experiments, and shape JigsawStack’s playbook for years to come.
Hey! Awesome product, not sure which model you use under the hood but you should check out https://jigsawstack.com/docs/api-reference/ai/vocr. Great for ID extraction which also includes bounding boxes and other attributes you'd need
We see two types: workflows & agents.
Workflows are the most common, there's a pipeline like processing loan documents before data gets loaded to the next step or translating user comments before being stored in the database.
Agents are where you have a chat based system or a brain of sorts that calls many tools to achieve a user goal. The model doing this is a lot better at non deterministic task which then delegates to Interfaze for specific deterministic actions like OCR, Web extract then consumes that data. That's the article you referenced :)