Hands-On Multimodal AI: Build Your First Interactive Apps
2 Weeks
·Cohort-based Course
Create Voice, Vision & Sensors-powered AI Apps in 14 Day—no ML expertise required.
Hands-On Multimodal AI: Build Your First Interactive Apps
2 Weeks
·Cohort-based Course
Create Voice, Vision & Sensors-powered AI Apps in 14 Day—no ML expertise required.
Previously at
Course overview
Hands-On Multimodal AI: Build Your First Interactive Apps
The Problem We're Solving Everyone’s cheering Gemini, GPT-4V and other Multimodal AI demos, yet most tutorials stop at “Hello World.”
You watch demos of AI that can see sketches and understand gestures, but the gap between inspiration and implementation feels insurmountable.
Meanwhile, stakeholders are presented with a significant opportunity to capitalize on the expanding market in multimodal AI.
Why This Course Is Different:
* Expert in your corner: Learn from someone building these systems at Google DeepMind, live workshops + Slack hotline with me.
* Hands-on focus : Walk away with 3 functional prototypes built based on project guides
* Discover best practices – Master tools that work fast and reliably( Google AI Studio and the Gemini API ecosystem) and learn how to use frameworks that run on devices (llama.cpp, Ollama).
* Tiny Cohort, Big accountability: Max 35 students, peer reviews, demo day. Get personalized feedback and tight accountability.
In just two weeks you’ll be shipping portfolio-ready apps that prove you can harness multimodal AI—even on a phone with no prior experience needed.
Who is this course for
01
Mid-Career Pivoters: Professionals (e.g. Marketing) seeking AI roles. Lack build experience, find ML theory dense. Need practical AI skills.
02
Designers/Creatives: UX/UI designers wanting AI in prototypes (voice, vision). Think coding is a barrier. Aim to rapidly build via APIs.
03
Product Managers: PMs needing to grasp multimodal APIs beyond text to define/prototype new AI-powered product features (voice, image).
What you’ll get out of this course
Demystify Multimodal AI & Start BUILDING
Go from feeling intimidated about AI to confidently creating your own simple, interactive multimodal applications using provided templates and bespoke no-code tools for using APIs for vision, voice, and other sensors.
Rapidly Prototype Your AI Ideas
Learn to take a cool ideas, perhaps inspired by novel AI ability to understand sketches or analyze video, and quickly build a working proof-of-concept. Think: a voice-activated note-taker, a gesture-controlled music player, or a tool that describes images aloud.
Add Tangible AI Skills to Your Resume/Portfolio
Showcase concrete, project-based experience with modern multimodal AI, crucial for career pivots or leveling up. You’ll leave with tangible projects and the empowerment to continue exploring.
"Speak AI" More Fluently & Design Better Interactions
Understand multimodal AI's real-world capabilities and limits to confidently discuss ideas, evaluate tools, and guide AI projects. Discover why effective interaction design—how vision, voice, and sensors work together—is often more crucial for success than just model accuracy.
What’s included
Live sessions
Learn directly from Stefania Druga in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Hands-On Multimodal AI: Build Your First Interactive Apps
Course syllabus
2 live sessions • 5 lessons • 3 projects
Week 1
Jul
2
Kick-Off – Voice & Vision Fundamentals
Wed 7/211:00 PM—12:00 AM (UTC)Jul
3
Interactive AI & Voice Integration
Thu 7/311:00 PM—12:00 AM (UTC)
Module 0: Multimodal AI Fast Track Prep
Week 1: Foundation Sprint – Vision & Voice
Week 2
Week 2: Advanced Integration & Capstone Prototype
What people are saying
Daria Dubois
Blake Harper
Meet your instructor
Stefania Druga
Stefania Druga
Stefania Druga is a former Research Scientist at Google DeepMind, where she worked on novel multimodal AI applications. She has a master's degree from MIT, PhD from UW and has been doing research on AI education since 2015. During graduate school, she built the first open-source platform for K12 AI Education - Cognimates . When she is not coding and writing papers, she enjoys trail running, yoga, and riding her bicycle.
Join an upcoming cohort
Hands-On Multimodal AI: Build Your First Interactive Apps
Regular
$649
Dates
Payment Deadline
Learning is better with cohorts
Active hands-on learning
This course builds on live workshops and hands-on projects
Interactive and project-based
You’ll be interacting with other learners through breakout rooms and project teams
Learn with a cohort of peers
Join a community of like-minded people who want to learn and grow alongside you
Join an upcoming cohort
Hands-On Multimodal AI: Build Your First Interactive Apps
Regular
$649
Dates
Payment Deadline