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
Smart PDF extraction system that identifies when no matching medicine is found. Extracts medicine names and prices from PDFs into clear, structured results.
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
Challenges
View all
Related posts
Weekly filming makes consistent video hard. Generic scripts can make your expertise sound interchangeable.
Here's how to turn your ideas into regular videos without filming every week.
My process:
1. AI agents help with ideas and research
2. AI first-draft scripting. Make sure you shape the message around your expertise and voice.
3. Review and approve the script before the avatar video is produced.
4. Schedule or hit publish!
The clip below is one finished example from my own socials. I use the same process with clients.
If you’re camera shy or too busy to film, book a call and bring one topic you’re thinking about sharing. Let's chat!
🔥 cool
Property App
A mobile real-estate product concept designed to make property discovery and search easier to navigate.
The experience focuses on clear property cards, structured listing information, intuitive search and a straightforward path from discovery to property details.
The goal was to reduce the friction that often comes with browsing large property inventories.
Design focus:
• Real Estate App Design
• Property Search UX
• Property Listings
• Mobile UI/UX
• Information Architecture
• Product Design
Designed by WaxyWeb.
Love it
I built Vetra, an AI technical interviewer that makes interviews more structured, adaptive, and realistic.
Vetra conducts real-time voice interviews, explores a candidate’s experience, adapts its questions based on their responses, evaluates performance, and generates structured assessments.
I built the interview orchestration with LangGraph, added real-time voice interaction using Gemini Live, and created a separate evaluation layer for evidence-based scoring.
The goal was to create an AI interview experience that feels more like a real technical conversation than a chatbot.
Jonathan, keeping the evaluation layer separate from the interviewer is a smart choice. When the same model asks and scores, it tends to grade its own questions kindly. How are you handling silence and long pauses on the voice side? That was the hardest part for us on a voice AI build.