Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
AI Call Analyst
Learn how to convert recruiter‑candidate call audio to text, assess pronunciation, apply business criteria with an LLM, score calls, and generate Word reports using Streamlit.
El desarrollo en el que estoy trabajando es un sistema que analiza audios de llamadas entre Reclutador y candidato (en inglés) y evalua la llamada del reclutador según critetios establecidos del negocio y también utiliza un modelo de Azure AI Service para evualuar su pronunciación. Todo esto se combina para darle una puntuación final de 0 a 100 al reclutador y ver en qué está fallando, al final se descarga un documento en word con todos los insights de la llamada, esto se hace utilizando los LLM de OpenAI, whisper de OpenAI y un modelo de Azure y se crea una interfaz con Streamlit
Related projects
Legal AI
Manizales
This talk covers developing a legal AI assistant using generative AI and retrieval-augmented generation to streamline legal research,…
The Future of AI: How Self-Improving AI is Changing the Game
Medellín
Explore why most AI systems underperform, learn the difference between monitoring and true optimization, and see how HandIt.ai…
AI-powered generation app and WhatsApp app
Pereira
Learn how to build a WhatsApp‑based system that collects photos, audio, and documents, then uses AI to generate…
Is AI alone capable to disrupt an industry?
Medellín
A live demo of bland.ai virtual human platform, followed by an analysis of whether AI-driven solutions alone can…
Building Magic the gathering decks using AI
Medellín
This talk explores building Magic: The Gathering decks using basic AI techniques like tf/idf to calculate card synergy…
Q&A session - Google deepmind research engineer
Medellín
An open Q&A covering DeepMind research methods, current projects, technical challenges, and career insights, allowing attendees to ask…