I need some feedback on the above statement
While checking the capability of large language models - I could see that the capability is good enough to extract required values from structured and unstructured documents
With above details - What is the future of document understanding module where we need to train the documents by labelling
Hi @sharazkm32
Even I have the same thought. The GenAI Activities were able to extract unstructured and structured data from PDF and Images much better.
@sharazkm32,
In my opinion, LLM is more of general purpose. It means, it can do everything possible with that LLM model.
Where as Document understanding uses Specialized AI which is targeted to the specific problem, Understanding various format and types of documents.
Document understanding modules provides you specialized tools to automated documents whereas LLM models are large scope which can be used for document automation but will require relatively more efforts than DU.
With Agent Builder around the corner, wouldn’t it be very overpowering and surpass the abilities of DU?
@V_Roboto_V,
That would be good to expect but as of now Agents also will be using existing DU bots as tools to complete the assigned tasks.
Though this is a good use case to do POC if Agents can replace DU. 
I tried Auto Pilot for everyone, and it could extract most of the fields without any training.