AI Co-Pilot for Multimedia Archives
This project aims to unlock the collective knowledge of the media industry — from SMPTE standards to decades of technical papers and conference recordings — by creating an AI-powered co-pilot assistant that transforms static archives into intelligent, searchable resources.
Tech Sponsor: Andy Beach
What is SMPTE and its iconic contributions?
For over 100 years, SMPTE (Society of Motion Picture and Television Engineers) has defined the technical foundations of film, television, and digital media. From the timecode and color bars used worldwide, to modern standards like ST 2110, SMPTE’s work shaped every stage of the media pipeline.
But all that knowledge — a century of engineering documents, meeting notes, standards, journal articles, conference papers, and multimedia archives — lives across large, fragmented, and difficult-to-search collections.
This project aims to change that!
You can join in different ways
CONTRIBUTOR
Join the project to help design, code, or document, every contribution counts toward moving the project forward.
INDUSTRY SUPPORTER
Help us validate the project in a production environment.
The time commitment is part-time and flexible! We understand that most participants have full-time jobs, so contributions can happen in your free time. We usually hold weekly 1-hour check-ins to keep everyone aligned, but there’s no fixed number of hours required.
This project is a three-month open collaboration where we combine exploration, research, and early prototyping. The goal isn’t to build a full product — it’s to understand how we can make a century of SMPTE knowledge more accessible through a responsible, open-source AI approach.
Although SMPTE’s archive spans a huge and diverse collection of technical materials, it remains challenging to search, contextualize, and navigate in a meaningful way.
With that spirit in mind, we defined a first objective that gives contributors a clear and structured path to learn, participate, and add value from day one.
Understand and define on the architecture of the Media Copilot
To do this, the project will focus on:
Learning the state of the art in AI approaches (including techniques such as RAG).
Exploring what already exists in the open-source community.
Gathering examples of prompts the Co-Pilot should answer and defining the expected outputs.
IA Copilot Project 2026 Meetings
56:04
43:07
How to get involved?
Follow the Repositories and Issues
@qualabs/smpte-copilot
Stay updated in video-dev.org Discord server
#project-smpte-copilot
Join the weekly calls
Every Friday
Get in Touch
Have a question or feedback?
Fill out the form below, and we’ll respond soon!
An event born from love, passion, and the desire to give back to the video community! 💜