Hello,
Welcome to our 5-Day Gen AI Intensive Course with Google! We’re glad you’re here.
This email includes a brief summary of how the course works and instructions on how to get set up. Tomorrow you’ll receive your first assignment.
How the Course Works
- Everyday, you’ll receive an email with assignments including the latest versions of all whitepapers, codelabs and podcast episodes.
- While completing the assignments, you’ll be able to ask questions and discuss with other participants on our Discord channel. The channel will be monitored by several Google ML researchers and engineers who can answer questions.
- Everyday, Paige Bailey will host a YouTube livestream at 11 AM PT / 7 PM CET / 11:30 PM IST starting on Monday, March 31st. She’ll be joined by special guests from Google.
- Throughout the event week, please make sure to complete all course content, including the codelabs, whitepapers, and podcast episodes.
- On the final day of the event, we will launch the capstone project, which will allow you to apply the knowledge you've gained throughout the course. By participating in the capstone project, you will earn a badge and a certificate on Kaggle.
Setup Instructions
-
Sign up for a Kaggle account and learn how Notebooks work. Make sure to phone verify your account, it’s necessary for the course’s codelabs.
-
Sign up for an AI Studio account and ensure you can generate an API key.
-
We also have a troubleshooting guide for the codelabs. Be sure to check there for solutions to common problems.
-
Sign up for a Discord account and join us on the Kaggle Discord server. We have the following channels dedicated to this event:
- #5dgai-announcements: find official course announcements and livestream recordings.
- #5dgai-introductions: introduce yourself and meet other participants from around the world.
- #5dgai-question-forum: Discord forum-style channel for asking questions and discussions about the assignments.
- #5dgai-general-chat: a general channel to discuss course materials and network with other participants.
-
Please note that if you would like to post on other channels on the Kaggle discord you will need to link your Kaggle account to discord here: https://kaggle.com/discord/confirmation.
Once you’ve got everything set up, please introduce yourself in the #5dgai-introductions channel on Discord. We are looking forward to meeting you!
See you soon,
The Kaggle Team
Hello,
🎒 Today’s Assignments
1. Complete the Intro Unit – “Foundational Large Language Models & Text Generation”:
- Listen to the summary podcast episode for this unit.
- To complement the podcast, read the “Foundational Large Language Models & Text Generation” whitepaper.
2. Complete Unit 1 – “Prompt Engineering”:
- Listen to the summary podcast episode for this unit.
- To complement the podcast, read the “Prompt Engineering” whitepaper.
- Complete these codelabs on Kaggle:
- Make sure you phone verify your Kaggle account before starting, it's necessary for the codelabs.
- Want to have an interactive conversation? Try adding the whitepapers to NotebookLM.
💡 What You’ll Learn
Today you’ll explore the evolution of LLMs, from transformers to techniques like fine-tuning and inference acceleration. You’ll also get trained in the art of prompt engineering for optimal LLM interaction and evaluating LLMs.
The first codelab will walk you through getting started with the Gemini 2.0 API and cover several prompt techniques including how different parameters impact the prompts. In the second codelab, you will also learn how to evaluate the response of LLMs using autoraters and structured output.
📋 Reminders
- Tomorrow at 11:00 AM PT, Paige Bailey is hosting the first livestream on our YouTube channel to discuss the assignments with the course authors and other special guests from Google. Tomorrow’s guests are Warren Barkley, Logan Kilpatrick, Kieran Milan, Anant Nawalgaria, Irina Sigler and Mat Velloso.
- Discord is the best place to ask questions – specifically in the #5dgai-question-forum channel. In addition to other participants, several Googlers are there to help. During the livestream, we'll also pick some questions from Discord to discuss. You'll get Kaggle swag if your question is chosen!
- We also have a troubleshooting guide for the codelabs. Be sure to check there for solutions to common problems.
- We want this course community to be positive and supportive. Please follow Kaggle’s community guidelines found here.
Happy learning and see you tomorrow!
The Kaggle Team
https://www.youtube.com/live/WpIfAeCIFc0
Hello,
🎒 Today’s Assignments
Complete Unit 2: “Embeddings and Vector Stores/ Databases”:
-
Listen to the summary podcast episode for this unit.
-
To complement the podcast, read the “Embeddings and Vector Stores/ Databases” whitepaper.
-
Complete these codelabs on Kaggle:
-
Want to have an interactive conversation? Try adding the whitepaper to NotebookLM.
💡 What You’ll Learn
Today you will learn about the conceptual underpinning of embeddings and vector databases, and how they can be used to bring live or specialist data into your LLM application. You’ll also explore their geometrical powers for classifying and comparing textual data as well as how to evaluate embeddings.
📋 Reminders and Announcements
- Find the complete list of scheduled livestreams here.
- The second livestream is tomorrow with Paige Bailey and special guests: Andre Araujo, Patricia Florissi, Alan Li, Anant Nawalgaria, Xiaoqi Ren, Chuck Sugnet and Howard Zhou.
- Be sure to ask all your questions about the podcast, readings, and code lab in the #5dgai-question-forum channel on Discord. You'll get Kaggle swag if your question is chosen for discussion during the livestream.
Happy learning and see you tomorrow!
The Kaggle Team
https://www.youtube.com/live/AjpjCHdIINU
Hello,
🎒 Today’s Assignment
1. Complete Unit 3a - “Generative AI Agents”:
-
Listen to the summary podcast episode for this unit.
-
To complement the podcast, read the . “Generative AI Agents” whitepaper
-
Complete these codelabs on Kaggle:
2. [Optional] Advanced 3b - “Agents Companion”:
- Listen to the summary podcast episode for this unit.
- Read the advanced “Agents Companion” whitepaper.
- Want to have an interactive conversation? Try adding the whitepaper to NotebookLM.
💡 What You’ll Learn
Learn to build sophisticated AI agents by understanding their core components and the iterative development process. You'll also learn more about advanced agentic architectures and approaches such as multi-agent systems, agent evaluation and more.
The codelabs cover how to connect LLMs to existing systems and to the real world. Learn about function calling by giving SQL tools to a chatbot (including an example using Gemini 2.0’s Live API), and learn how to build a LangGraph agent that takes orders in a café.
📋 Reminders and Announcements
- Find a complete list of scheduled livestreams and past recordings here.
- The next livestream is tomorrow at 11 AM PT / 7 PM CET / 11:30 PM IST. Click here to join! Livestream guests: Alan Blount, Antonio Gulli, Steven Johnson, Jaclyn Konzelmann, Patrick Marlow, Anant Nawalgaria and Julia Wiesinger.
- Be sure to ask all your questions about the podcast, readings, and codelabs in the #5dgai-question-forum channel on Discord. You'll get Kaggle swag if your question is chosen for discussion during the livestream.
Happy learning and see you tomorrow!
The Kaggle Team
https://www.youtube.com/live/g6MVIEzFTjY
Hello,
🎒 Today’s Assignments
Complete Unit 4 - “Domain-Specific LLMs”:
-
Listen to the summary podcast episode for this unit.
-
To complement the podcast, read the “Solving Domain-Specific Problems Using LLMs” whitepaper.
-
Complete these codelabs on Kaggle:
-
Want to have an interactive conversation? Try adding the whitepaper to NotebookLM.
💡 What You’ll Learn
In today’s reading, you’ll delve into the creation and application of specialized LLMs like SecLM and MedLM/Med-PaLM, with insights from the researchers who built them.
In the codelabs, you'll learn how to add real-world data to a model using Google Search and then visualize it with plotting tools via the Live API. You will also learn how to fine-tune a custom Gemini model using your own labeled data to solve custom tasks.
📋 Reminders and Announcements:
- Find the complete list of scheduled livestreams and past recordings here.
- The next livestream with Paige Bailey is tomorrow at 11 AM PT / 7 PM CET / 11:30 PM IST. Click here to join! Livestream guests: Donny Cheung, Scott Coull, Ewa Dominowska, Chris Grier, Anant Nawalgaria and Karthik Raman.
- Be sure to ask all your questions about the podcast, readings, and codelabs in the #5dgai-question-forum channel on Discord. You'll get Kaggle swag if your question is chosen for discussion during the livestream.
Happy learning and see you tomorrow!
The Kaggle Team
https://www.youtube.com/live/AN2tpHi26OE
Hello,
We’ve reached the last day’s assignment! 🎉
🎒 Final Assignment
Complete Unit 5 - “MLOps for Generative AI”:
- Listen to the summary podcast episode for this unit.
- To complement the podcast, read the “MLOps for Generative AI” whitepaper.
- No codelab for today! During the livestream tomorrow, we will do a code walkthrough and live demo of goo.gle/agent-starter-pack, a resource created for making MLOps for Gen AI easier and accelerating the path to production. Please go through the repository in advance.
- Want to have an interactive conversation? Try adding the whitepaper to NotebookLM.
💡 What You’ll Learn
Discover how to adapt MLOps practices for Generative AI and leverage Vertex AI's tools for foundation models and generative AI applications such as AgentOps for agentic applications.
📋 Reminders and Announcements
- Find the complete list of scheduled livestreams and past recordings here.
- The final livestream is tomorrow at 11 AM PT / 7 PM CET / 11:30 PM IST hosted by Paige Bailey with special guests: Sokratis Kartakis, Gabriela Hernandez Larios, Ivan Nardini, Anant Nawalgaria, Elia Secchi, Michael Styer and Saurabh Tiwary.
- Be sure to ask all your questions about the podcast and readings in the #5dgai-questions-2 channel on Discord.
Happy learning and see you tomorrow!
The Kaggle Team
https://www.youtube.com/live/eZ-8UQ_t4YM
Hello,
Congrats on finishing the 5-day Generative AI Intensive course! As we wrap things up, this is our final round up of reminders and announcements.
📋 Reminders and Announcements
- 🎯 Capstone Project: Level up your skills and enhance your portfolio with a real-world capstone project. You’ll create a notebook showcasing a use case that leverages some of the key generative AI capabilities learned throughout this course. For bonus points, you’ll have the option to create a blog post and/or YouTube video around your use case. The top 10 winners will have their work featured on Kaggle and Google Cloud’s social media. Additional details about the capstone project, evaluation, and submission process will be shared in another email today. Participation in the capstone project is optional.
- ⭐ Kaggle badge and certificate: You are eligible to earn a badge and certificate on your Kaggle profile for participating in the capstone project. The badges and certificates will be added to your profile by the end of April 2025.
- 👀 Look out for the Kaggle Learn Guide: All of the course content will be aggregated and made publicly available next week as a handy Kaggle Learn Guide. We’ll share it with you as soon as it's ready. In the meantime, all of the livestream recordings can be found here.
- 🎟️ Google Cloud NEXT: If you happen to be at Google Cloud NEXT this year, don’t forget to drop by at the “Become a GenAI Expert” session led by Paige Bailey and Anant Nawalgaria. We will also be giving out limited copies of the abridged whitepapers at the Coding Challenge hub. We hope to see you there!
- 📢 Share your feedback: Please fill out this quick feedback form to let us know more about your experience. It’ll help us improve the program for future participants. Your feedback is completely anonymous and should only take a few minutes.
And with that, thank you very much for joining us this week. We enjoyed connecting with you all, and wish you nothing but the best as you continue to grow your skills in this field.
Cheers,
The Kaggle Team