The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Designed and developed an AI-powered document automation workflow that processes unstructured documents using OCR and LLM-based extraction techniques. The system converts scanned PDFs and text-heavy files into clean, structured outputs for easier analysis, validation, and workflow integration. Built with Python and focused on scalable, real-world automation use cases.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?
Related posts
The free AI rebuild prompt for Sunbeam’s homepage is now live on my website
Just hit “Get the prompt” and follow the instructions.
Sol 5.6 or Fable 5 will one shot it
AI create super cool websites
Human by Design
This project explores the relationship between human creativity and AI—not as competitors, but as collaborators.
Rather than creating a fully AI-generated film, I focused on documenting a real creative workflow.
The screen recordings of ChatGPT and Envato are real, and most of the visuals were created using Envato Elements assets. AI was intentionally used for only a small number of cinematic shots to support the narrative, while the creative direction, research, prompt development, editing, and storytelling remained human-led.
ChatGPT served as a creative collaborator throughout the project, helping me refine the concept, structure the narrative, improve prompts, and strengthen the overall story.
The goal wasn't to show what AI can create alone—but what humans can create when they know how to direct it.
Proud to submit this project for the Envato × Contra AI Creative Challenge.
#HumanByDesign #Contra #Envato #AI #CreativeDirection #PromptEngineering #DesignProcess #GenerativeAI
This caught my attention immediately. The transitions are really well executed. I'm curious—what part of the creative process took the longest for you?
A realtor or a business in need of python and LLM AI document processing? Here are some recaps of my previous internship I did.
Just completed some advanced level python and LLM from extern for a mortgage company.
Check out some of the project I've worked on
Engineered AI-powered document processing pipelines for 200+ page mortgage files using OCR technologies including Tesseract OCR, PaddleOCR, and PyMuPDF, enabling scalable document extraction and parsing.
Developed a Retrieval-Augmented Generation (RAG) system using LlamaIndex for intelligent document search, classification, and contextual retrieval workflows.
Improved retrieval accuracy and system performance through embedding optimization, chunking strategies, vector search tuning, and intelligent routing logic.
Delivered technical documentation, demo UI, and evaluation reports validating OCR accuracy, retrieval precision, and system readiness for production deployment.
github.com
GitHub - Kyl67899/Outamation_Externship_internship
Contribute to Kyl67899/Outamation_Externship_internship development by creating an account on GitHub.
The OCR plus RAG pipeline for 200-page mortgage files sounds like a serious test of retrieval quality. Which document type caused the toughest extraction or chunking issue?