Prompt Engineering with Gemini

Prompt Engineering with Gemini

English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 1h 2m | 158 MB

Gemini (formerly known as Bard) is a generative AI model from Google with powerful multimodal capabilities and integrations. In this course, Denys Linkov gives an introduction to Gemini, showing you how to perform a variety of everyday tasks like brainstorming ideas, writing emails, browsing the web, and even planning a vacation. He covers advanced prompts you can use to improve results, and illustrates multimodal functionality by showing you how you can use Gemini to analyze and generate images and search and summarize YouTube videos.

Table of Contents

Introduction
1 Learning prompt engineering with Gemini

Introduction to Gemini
2 Enabling Gemini
3 Writing your first prompt

Using Gemini Day-to-Day
4 Brainstorming with Gemini
5 Iterating with Gemini
6 Improving your writing with Gemini
7 Browsing the web with Gemini
8 Introduction to Gemini extensions
9 Planning a vacation with Gemini
10 Challenge Writing copy for your new activewear brand
11 Solution Writing copy for your new activewear brand

Advance Your Prompts to Improve Results
12 Improving prompting with examples and quotes
13 Using completion sequences and few-shot learning
14 Using chain-of-thought reasoning
15 Reformatting your data nicely
16 Challenge Give Gemini a tricky problem
17 Solution Give Gemini a tricky problem

Multi-Modal Gemini
18 Image recognition and augmentation with Gemini
19 Creative image generation
20 Analyzing a multi-modal document with Gemini
21 Searching and summarizing a YouTube video with Gemini
22 Challenge Comparing two world wonders
23 Solution Comparing two world wonders

Conclusion
24 Continuing your prompt engineering journey

Homepage