BrighterTube

Building Multimodal AI Agents From Scratch — Apoorva Joshi, MongoDB

AI Engineer1.01M subscribers

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Teaches building multimodal AI agents that process text, images, and other inputs from scratch. Explains architecture and implementation for agents handling multiple data types.

A 37-minute video from AI Engineer: “Building Multimodal AI Agents From Scratch — Apoorva Joshi, MongoDB”.

Programming & CS

Video by AI Engineer, played through YouTube's embedded player.

Part of Full Workshops: AI Engineer World's Fair 2025