Multimodal AI
Open a video or resource link, watch it, then check its box to track your progress and unlock what comes next.
Build systems that reason across text, images, audio, and video; learn multimodal prompting, representation, grounding, OCR/vision patterns, audio pipelines, latency/cost constraints, and evaluation.
- Multimodal AI — Google Cloud Tech (7 min)
Concrete application that processes video, audio, and text, including a code walkthrough. - Generative AI for Beginners — Microsoft Developer (25 min selected)
Use the multimodal/application chapters to connect vision and language workflows. - Fine- tuning Open LLMs on GKE — Google Cloud Tech (7 min)
Shows how multimodal adaptation changes data and production requirements.
- Transformers — 3Blue1Brown
A deeper treatment of the same skill; use it to move from concept to working patterns. - Introduction to MCP Servers — Microsoft Build
Apply Multimodal AI through the adjacent capability: Tool Use & Function Calling. - Tips for Building AI Agents — Anthropic
Apply Multimodal AI through the adjacent capability: Tool Use & Function Calling.
- Build an MCP Server in 20 Minutes — pixegami
Extend Multimodal AI into senior/production practice through Tool Use & Function Calling. - MCP Workshop — Anthropic
Extend Multimodal AI into senior/production practice through AI Agents. - Agent Service SDK Demo — Microsoft Azure
Extend Multimodal AI into senior/production practice through AI Experience Engineering.