AI Instructor Live Labs Included

GCP: Google AI Studio

Master Google AI Studio: prototype prompts, tune model settings, compare models, and export working Python code to build production Gemini applications.

Beginner

12h 50m

8 Lessons

About This Course

Learn to prototype, test, and export Gemini prompts using Google AI Studio the browser-based development environment for Gemini models. You'll master prompt types, model settings, system instructions, model comparison, and the complete workflow from AI Studio prototype to production Python code.

Course Curriculum

8 Lessons

AI Lesson

GCP: Introduction to Google AI Studio

1h 0m

Explore Google AI Studio — the browser-based interface for prototyping Gemini prompts. Learn the workspace layout, prompt types, model settings, and how to export working code directly to Python.

Lab Exercise

GCP: Prototyping with AI Studio

2h 5m 4 Exercises

Use Google AI Studio hands-on to prototype prompts, tune model settings, and export working Python code into VS Code. You'll build a structured few-shot classifier and a multi-turn chat prompt, then run the exported code in your VS Code environment.

Explore AI Studio and Run Your First Freeform Prompt Navigate Google AI Studio, familiarize yourself with the interface, and run a freeform prompt. Then export the generated Python code and run it in VS Code. ~20 min

Build a Few-Shot Classifier with Structured Prompts Use AI Studio's Structured prompt mode to build a sentiment classifier with few-shot examples. Tune temperature to 0.0 for deterministic output, then export and run the classifier in VS Code. ~20 min

Design a Multi-Turn Chat with System Instructions Use AI Studio's Chat prompt mode to design a persona with system instructions. Test the persona across 4 conversation turns, then export and run the code in VS Code using the system_instruction parameter. ~25 min

Use Prompt Variables and Save to Your Library Create a reusable prompt template using AI Studio's {{variable}} syntax, test it with multiple variable values, save it to your prompt library, and export the parameterized code to VS Code. ~15 min

AI Lesson

GCP: Advanced AI Studio — System Instructions & Evaluation

1h 0m

Deep dive into AI Studio's advanced features: system instructions for persistent model behavior, the prompt gallery for inspiration, model comparison, and using AI Studio's built-in evaluation tools to test prompt robustness.

Lab Exercise

GCP: AI Studio to VS Code — Building a Prompt Pipeline

2h 15m 4 Exercises

Use advanced AI Studio features hands-on: write system instructions, compare models, save prompts to your library, then export and extend the code in VS Code to build a reusable prompt pipeline with parameterization and error handling.

Build a System Instructions Persona in AI Studio Write system instructions for a custom AI persona in AI Studio's Chat mode, test it across multiple turns, then export the code and implement the full conversation runner in VS Code. ~20 min

Benchmark Two Models with the Compare Feature Use AI Studio's Compare feature to run the same prompt on two Gemini models side by side. Then implement a Python benchmark in VS Code that measures response time and token usage for each model. ~20 min

Build a Reusable PromptPipeline Class Implement a PromptPipeline class that accepts a template string with {variable} placeholders, fills them at runtime, and supports both single-run and batch modes. Test it with a summarizer and a sentiment classifier. ~25 min

Add Error Handling and Retry Logic to the Pipeline Upgrade PromptPipeline to RobustPromptPipeline by adding input validation, exponential backoff retry on rate limit errors, and graceful safety filter handling. Test all three code paths. ~25 min

AI Lesson

GCP: AI Image Generation — Nano Banana 2 and Pro

45m

Learn how Google's Nano Banana image generation models work — Nano Banana 2 (gemini-3.1-flash-image-preview) for fast, high-volume generation and Nano Banana Pro (gemini-3-pro-image-preview) for maximum quality with built-in thinking. Understand the image generation API, response_modalities, ImageConfig parameters, and when to choose each model.

Lab Exercise

GCP: Hands-On Image Generation with Nano Banana

2h 25m 4 Exercises

Use the Gemini image generation API in VS Code to generate images from text prompts, edit reference images, build a multi-turn image editing session, and compare the quality output of Nano Banana 2 versus Nano Banana Pro. All exercises use the new google-genai SDK.

Generate Images from Text with Nano Banana 2 Use the Gemini image generation API with Nano Banana 2 (gemini-3.1-flash-image-preview) to generate images from text prompts. You'll install the dependencies, set up your API key, generate your first image, experiment with aspect ratios and sizes, and save images to disk. ~25 min

Edit Images with Reference Input Pass a reference image alongside an edit instruction to Nano Banana 2. You'll load a downloaded reference image, send it to the model with various editing prompts (background change, style transfer, object addition), and compare the edited outputs. ~25 min

Multi-Turn Image Editing with Chat Sessions Use client.chats.create() with an image generation model to build a multi-turn editing workflow. Generate an initial scene, then iteratively refine it across three conversation turns, with each turn building on the model's memory of the previous image. ~25 min

Nano Banana Pro — High-Fidelity Generation and Quality Comparison Switch to Nano Banana Pro (gemini-3-pro-image-preview) and generate the same prompts used in Exercise 1. Compare the outputs side-by-side to see the quality difference, use 4K resolution (Pro-only), and understand when the quality uplift justifies the cost. ~25 min

AI Lesson

GCP: AI Studio Tools — Search, Code Execution & Structured Output

50m

Learn Google AI Studio's four most powerful built-in tools: Grounding with Google Search for real-time facts, Code Execution for in-browser Python running, Structured Output for guaranteed JSON responses, and Function Calling for API integration. Also covers multimodal file uploads — PDF documents, audio, and video.

Lab Exercise

GCP: Using AI Studio Tools in Python

2h 30m 5 Exercises

Implement all four AI Studio power tools in VS Code using the google-genai SDK: Grounding with Google Search, Code Execution, Structured Output with JSON schemas, and Function Calling. Also covers uploading PDF and audio files to the Gemini Files API for long-document and audio analysis.

Grounding with Google Search Enable real-time web search in Gemini responses using the GoogleSearch tool. You'll compare grounded vs. ungrounded answers for time-sensitive queries, parse citation metadata, and build a research assistant that cites its sources. ~20 min

Code Execution — Run Python Inside Gemini Enable the Code Execution tool so Gemini can write and run Python to verify its own calculations. You'll see the executable_code and code_execution_result parts in the response, use it for data analysis, and understand when code execution eliminates hallucinations. ~20 min

Structured Output — Guaranteed JSON Responses Use response_mime_type and a Pydantic schema to force Gemini to return valid, parseable JSON. You'll define schemas for sentiment analysis, entity extraction, and a product catalog parser, then call json.loads() directly on the response with no cleanup needed. ~20 min

Function Calling — Connect Gemini to External APIs Define FunctionDeclarations that Gemini can invoke when it needs external data. You'll implement a weather lookup tool, handle the function_call response part, return results back to the model, and build a two-tool assistant that combines weather and currency conversion. ~25 min

File Uploads — Analyze PDFs and Audio with the Files API Upload PDF documents and audio files to Gemini's Files API and ask questions about their content. You'll generate a test PDF, upload it, query across multiple pages, then upload an audio file for transcription and summarization. ~20 min

This course includes:

24/7 AI Instructor Support
Live Lab Environments
4 Hands-on Lessons
6 Months Access
Certificate of Completion