Applied Use Cases

Applied Use Cases on Google Cloud are practical, end-to-end generative AI patterns that combine Gemini models, Vertex AI, Agent Platform, BigQuery, embeddings, search, speech, evaluation, and tuning services to solve domain workflows. The notebooks emphasize implementation mechanics: authentication, IAM, data preparation, model orchestration, evaluation, deployment, and cleanup.

Synthesized across 88 notebooks. See the source pages under Notebooks below for line-level grounding.

This area is less about isolated prompting and more about wiring generative models into real systems: agents with tools and memory, analytics agents over BigQuery or Looker, RAG over documents or code, BigQuery AI functions, vector search, speech generation, image generation, and multimodal analysis.

Most workflows start from a Google Cloud project with billing, API enablement, authentication, project and location configuration, and precise IAM. The recurring engineering pattern is to prepare trustworthy context, call Gemini or embedding models through the right surface, constrain outputs with schemas or tools, persist intermediate results, and verify behavior with evaluation or inspection.

The material repeatedly treats notebooks as prototypes, not finished production systems. Productionization requires deterministic settings where appropriate, explicit permissions, retries and polling for long-running jobs, cost cleanup, managed retrieval or indexing services at scale, and careful handling of preview, allowlisted, regional, or quota-sensitive features.

Canonical workflow

1. Define the use case, data sources, output shape, and whether the workflow needs agents, RAG, BigQuery SQL, speech, image generation, tuning, or evaluation.
2. Prepare the Google Cloud environment: set PROJECT_ID and LOCATION, authenticate, enable required APIs, configure billing, and grant least-privilege IAM to users, service accounts, and BigQuery connections.
3. Prepare data and context: load documents, tables, logs, code, images, audio, examples, glossary terms, golden queries, memory topics, or tool specifications as required by the workflow.
4. Select the appropriate model and API surface, such as Gemini through Vertex AI or google-genai, embeddings, Text-to-Speech, Vertex AI Agent Engine, Gemini Data Analytics, BigQuery AI functions, Vector Search, or Memory Bank.
5. Prototype the core call path with structured prompts, response schemas, function declarations, retrieved context, deterministic generation settings when needed, and explicit parsing/error handling.
6. Persist and inspect intermediate outputs such as generated fields, embeddings, memories, summaries, artifacts, evaluation rows, BigQuery tables, GCS files, or vector indexes before building downstream steps.
7. Evaluate and iterate using task-specific metrics, row-level explanations, model comparisons, retrieval quality checks, tuned-vs-base comparisons, or manual inspection of generated outputs.
8. Operationalize cautiously: deploy agents or indexes, poll long-running operations, add retries/backoff, preserve IAM policies, monitor logs, and clean up billable resources when finished.

Best practices

See Applied Use Cases - Best Practices for the full distilled guide.

• Start every notebook workflow by validating project, billing, API enablement, authentication, quota project, location, and required IAM roles before making model or service calls.
• Use explicit system instructions, domain context, examples, glossary terms, golden queries, topic descriptions, and tool instructions so the model has the business and data context needed for reliable behavior.
• Constrain model outputs with response schemas, JSON MIME types, OpenAPI-style function parameters, typed BigQuery AI functions, or output_schema when downstream code must parse or query the result.
• Test tool functions, retrieval calls, BigQuery queries, and local agent behavior directly before wiring them into deployed agents, graphs, or multi-step orchestration.
• Use low temperature or fixed seeds where the workflow needs repeatable routing, classification, tool arguments, search-agent behavior, or evaluation outputs, while still accounting for possible variation.
• Ground answers in retrieved or connected data rather than pretrained knowledge for domain-specific workflows, and keep metadata such as page, chunk, source document, filename, or table context with retrieved content.

Key models & APIs

• gemini-2.5-flash, gemini-2.0-flash, gemini-3.5-flash, gemini-2.0-flash-live-preview-04-09, gemini-2.5-flash-image-preview, text-embedding-005, gemini-embedding-001, multimodalembedding@001, lyria-3-clip-preview, lyria-3-pro-preview, Chirp 3 Instant Custom Voice, text-bison@001, claude-3-haiku@20240307, TimesFM, Vertex AI API and Google Gen AI SDK, Vertex AI Agent Engine and Managed Agents API, Vertex AI Memory Bank, Gemini Data Analytics DataA2AService, HTTP API, and A2A SDK, Agent Platform Vector Search and Vector Search 2.0, BigQuery AI functions including AI.GENERATE, AI.GENERATE_TABLE, AI.SCORE, AI.CLASSIFY, AI.IF, AI.GENERATE_BOOL, AI.GENERATE_INT, and AI.GENERATE_DOUBLE, BigQuery ML functions including ML.GENERATE_TEXT, ML.GENERATE_EMBEDDING, VECTOR_SEARCH, ML.DESCRIBE_DATA, ML.EVALUATE, ML.CENTROIDS, and ML.PREDICT, Vertex AI Search and Discovery Engine, Cloud Text-to-Speech API, Cloud Storage, Document AI, Vertex AI EvalTask and Rapid Evaluation, LangChain, LangGraph, CrewAI, Phoenix, and Gradio

Notebooks (88)

Agents & ADK (7)

• Customizing Memory Topics — Customizes Vertex AI Memory Bank topics for a financial advisor assistant and compares default vs custom extraction.
• Governance with Vertex AI Memory Bank — Builds a governed Vertex AI Memory Bank with TTL, topics, revision history, rollback, and cleanup.
• Gemini Data Analytics: A2A HTTP API Sample — Calls Gemini Data Analytics DataA2AService over HTTP for agent cards, messages, artifacts, and cancellation.
• Gemini Data Analytics: A2A SDK API Sample — Uses the A2A Python SDK to send synchronous-style requests to Gemini Data Analytics.
• Intro to Gemini Data Analytics — Shows REST-based Gemini Data Analytics agents over BigQuery, Looker, or Looker Studio data.
• Intro to Gemini Data Analytics — Shows how to create Gemini Data Analytics agents over BigQuery, Looker, or Looker Studio and chat with them.
• Managed Agents API - Analyzing the 2026 World Cup — Deploys a Managed Agents API World Cup analyst agent with GCS skills and multi-turn interactions.

Audio (4)

• Lyria 3 Music Generation — Generates Lyria 3 music tracks, clips, lyrics, and streams with the Google Gen AI SDK.
• Get started with Chirp 3: Instant custom voice — Creates and uses a Chirp 3 Instant Custom Voice with Cloud Text-to-Speech and a Gradio app.
• Create a Multi-Speaker Podcast with Gemini 2.0 & Text-to-Speech — Generates a two-speaker podcast from a PDF using Gemini JSON output and Text-to-Speech MP3 synthesis.
• Narrate a Multi-character Story with Gemini and Text-to-Speech — Generates a Gemini play script and narrates it with distinct Text-to-Speech voices per character.

Embeddings & Vector Search (4)

• Combining Semantic & Keyword Search: A Hybrid Search Tutorial with Agent Platform Vector Search — Builds sparse and hybrid Vector Search indexes for Google Merch Shop product search.
• Log Anomaly Detection & Investigation with Text Embeddings + BigQuery Vector Search — Detects audit log anomalies using text-embedding-005 embeddings and BigQuery VECTOR_SEARCH.
• Anomaly Detection of Infrastructure Logs using Gemini and BigQuery Vector Search — Detects HDFS log anomalies with Gemini summaries, text embeddings, and BigQuery Vector Search.
• Introduction to Agent Platform Vector Search 2.0 — Builds an e-commerce product search demo with Agent Platform Vector Search 2.0 and auto-embeddings.

Gemini (60)

• AG2 (formerly Autogen) Multi-Agents Example on Vertex AI Agent Engine — Builds and deploys an AG2 multi-agent research app to Vertex AI Agent Engine.
• Building and Deploying a Google Maps API Agent with Agent Engine — Builds, tests, deploys, and queries a Gemini Google Maps agent on Vertex AI Agent Engine.
• Building a Conversational Search Agent with Agent Engine and RAG on Vertex AI Search — Builds and deploys a Gemini movie-search RAG agent with LangChain, Agent Engine, and Vertex AI Search.
• Semantic Router Agent — Builds a LangGraph semantic router that sends retail queries to mocked Gemini expert assistants.
• Migrate from PaLM to Gemini model — Compares PaLM text-bison and gemini-2.5-flash with Vertex AI EvalTask for summarization migration.
• Evaluate LangChain — Evaluates a LangChain recipe chatbot with Vertex AI Rapid Evaluation and custom Gemini-based metrics.
• Evaluating multimodal task — Evaluates image-grounded car damage labels with Vertex AI EvalTask and a Gemini custom autorater.
• Overview — Evaluates a CrewAI research crew with Phoenix tracing and Vertex AI trajectory metrics.
• Intro to Function Calling with the Gemini API & Python SDK — Introduces Gemini function calling in Vertex AI with chat tools, mock API responses, and live geocoding.
• Real-time Retrieval Augmented Generation (RAG) using the Multimodal Live API with Gemini 2.0 — Builds a retail RAG pipeline with Gemini Multimodal Live API for grounded text and audio answers.
• Nano Banana 🍌: Gemini 2.5 Flash Image Recipes — Demonstrates Gemini 2.5 Flash image generation and editing recipes on Vertex AI with google-genai.
• From API to Report: Building a Currency Analysis Agent with LangGraph and Gemini — Builds a LangGraph currency analysis agent using Gemini on Vertex AI and an exchange-rate API.
• Chain of Thought & ReAct — Demonstrates CoT prompting and ReAct agents with Vertex AI, LangChain, Wikipedia, and BigQuery.
• Text Summarization with Generative Models on Vertex AI — Demonstrates Gemini text summarization prompts on Vertex AI and evaluates summaries with ROUGE.
• Get Started with Gemini Preference Optimization — Tunes Gemini 2.5 Flash with human preference data using Vertex AI preference optimization.
• Supervised Fine-tuning Gemini 2.5 Flash for Predictive Maintenance — Fine-tunes Gemini 2.5 Flash on simulated sensor data to classify equipment maintenance status.
• Supervised Fine-tuning Gemini 2.5 Flash for Visual Defect Detection — Fine-tunes Gemini 2.5 Flash on image-based manufacturing defect classification.
• AI-Assisted Data Science Workflows in BigQuery — Builds a BigQuery multimodal housing workflow with Gemini enrichment, BQML clustering, and vector search.
• Analyzing movie posters in BigQuery with Gemini — Analyzes movie poster images in BigQuery with Gemini, embeddings, and vector search.
• Semantic Analysis in BigQuery with AI Functions — Uses BigQuery AI functions with Gemini to rank, classify, filter, join, and enrich pet product data.
• BigQuery DataFrames ML: Prescription Drug Name Generation — Generates pharmaceutical brand name ideas with BigQuery DataFrames ML and Gemini.
• Text + multimodal embedding generation and vector search in BigQuery — Builds text and image embeddings in BigQuery for semantic product search.
• Introduction to Generative AI functions in BigQuery — Introduces BigQuery generative AI functions for SQL-based text analysis and forecasting.
• Test Document AI Gemini — Compares Document AI entity extraction with Gemini-based extraction on a PDF.
• Analyze Multimodal Data in BigQuery — Shows BigQuery multimodal analysis over structured tables and GCS media using ObjectRefs and Gemini.
• Performing Semantic Search in BigQuery — Builds semantic search over Stack Overflow questions in BigQuery with Vertex AI text embeddings.
• Analyze a codebase with Gemini in Vertex AI — Uses Gemini 3.5 Flash on Vertex AI to analyze, document, debug, and extend a GitHub codebase.
• Use Retrieval Augmented Generation (RAG) with Gemini API — Builds a LangChain RAG pipeline over GitHub code notebooks using Gemini and Vertex AI embeddings.
• Code Vulnerability Scanning & Automated Remediation using Gemini API in Vertex AI (Gemini 2.0) — Scans Python files from GCS with Gemini 2.0 Flash and exports vulnerability reports to CSV and JSON.
• Reduce Tech Debt with Gemini 3 Pro — Uses Gemini 3.1 Pro on Vertex AI to refactor legacy Python code through tests, specs, design docs, and verification.
• Comparing LlamaIndex and LlamaParse for Dense Document Questioning Answering on Vertex AI — Compares LlamaIndex and LlamaParse RAG parsing methods for dense 10-Q document QA on Vertex AI.
• Document Processing with Gemini — Processes PDFs with Gemini on Vertex AI for extraction, classification, QA, summarization, translation, and page selection.
• Patents Document Understanding with Gemini — Uses Gemini batch prediction on Vertex AI to extract structured fields and figure boxes from patent PDFs.
• Sheet Music Analysis with Gemini — Uses Gemini on Vertex AI to extract and edit sheet music PDF metadata and identify a song from audio.
• Text Summarization of Large Documents using LangChain 🦜🔗 — Summarizes large PDFs with LangChain and Gemini using stuff, map-reduce, and refine chains.
• Automating Income Taxes with Gemini — Classifies tax PDFs and extracts structured tax fields with Gemini on Vertex AI.
• Using Gemini in Education — Demonstrates Gemini education prompts across text, math, images, multiple images, and video.
• Evaluate — Evaluates Gemini-based document classification on image samples and visualizes confusion matrices.
• ReAct (Reasoning + Acting) + Custom tool for Healthcare NL API + Gemini 2.0 + LangChain — Builds a LangChain ReAct agent using Gemini 2.0 and Healthcare NLP to suggest medical billing codes.
• Building Knowledge Graphs with Gemini — Extracts knowledge graphs from text and PDF documents with Gemini using deterministic prompts and TSV outputs.
• Know Your Customer Use Case - Gemini Grounding with Google Search — Builds grounded Gemini KYC negative-news reports and evaluates response quality with custom Vertex AI metrics.
• Creative Content Generation with Gemini in Vertex AI and Imagen — Generates and personalizes GShoe marketing copy with Gemini, then outpaints product images with Imagen.
• Video Data Curation - Video Quality Filtering — Filters video datasets by metadata, OCR/watermarks, aesthetics, and motion scores for curation.
• Data Curation Pipeline: Splitting and Transcoding — Deduplicates video clips using video embeddings and BigQuery vector search.
• Data Curation Pipeline: Splitting and Transcoding — Builds a video curation pipeline for metadata filtering, splitting, scene detection, and transcoding.
• Multimodal Sentiment Analysis with Gemini — Compares Gemini sentiment analysis on audio versus a transcript of the same conversation.
• Productivity Coaching with Gemini and Google Calendar — Uses Gemini 2.5 Flash with Google Calendar data to provide productivity coaching and schedule recommendations.
• Slide Generation with Gemini and Marp — Uses Gemini and Marp to turn a blog post into a Markdown slide deck and PDF.
• Multimodal retail recommendation: using Gemini to recommend items based on images and image reasoning — Builds a Gemini multimodal retail recommender that explains chair fit for a room image.
• Retail AI Location Strategy: Autonomous Site Selection & Market Analysis — Builds a Gemini 3 retail site-selection pipeline using search, Maps, code execution, reasoning, and JSON output.
• RAG Based on Sensitive Data Protection using Faker — Builds a RAG flow that anonymizes PII with Cloud DLP, Faker, Firestore, Chroma, and Gemini.
• Intra Knowledge QnA — Builds a Vertex AI and LangChain RAG Q&A app over an IRS PDF using Chroma embeddings.
• Retrieval Augmented Generation(RAG) with AlloyDB — Builds a RAG workflow over patent abstracts using AlloyDB vector search and Gemini on Vertex AI.
• Building a Gen AI RAG application with Vertex AI Feature Store and BigQuery — Builds a LangChain RAG Q&A app using BigQuery Vector Search and Vertex AI Feature Store.
• Augment Gemini Output with Vector Embeddings from BigQuery — Builds BigQuery vector-search RAG over patent abstracts and uses Gemini to generate project ideas.
• Run RAG Pipelines in BigQuery with BQML and Vector Search — Builds a BigQuery RAG pipeline over a PDF using Document AI, embeddings, vector search, and Gemini.
• Spatial understanding with Gemini 3 — Uses Gemini 2.5 Flash on Vertex AI to detect objects and draw normalized bounding boxes on images.
• Identifcation of Scene Transitions in Movies Using Gemini — Uses Gemini to detect movie scene transitions from a video and matching VTT subtitles.
• YouTube Video Analysis with Gemini — Analyzes public YouTube videos with Gemini for summaries, structured JSON extraction, and cross-video insights.
• Enhanced Vision Assistant with Gemini — Builds a Gemini vision assistant that detects objects, assesses hazards, and speaks navigation guidance.

Open Models (5)

• Qwen 3 evaluation - Bring your own data eval — Compares fine-tuned and base Qwen 3 medical summaries using Vertex AI pairwise evaluation.
• Hugging Face DLCs: Using Gemma for running evaluations with Vertex AI Gen AI Evaluation — Deploys Gemma 2 on Vertex AI TGI and evaluates summarization with Gen AI Evaluation.
• Deploying Multiple LoRA Adapters on Vertex AI with vLLM — Deploys Gemma 2 with multiple LoRA adapters on Vertex AI using a custom vLLM container.
• Use Any OSS Gen AI Model Against Your BigQuery Data — Deploys Llama 3.3 70B on Vertex AI and calls it from BigQuery ML for medical transcript analytics.
• Deploying Llama 3 on Google Kubernetes Engine with Cloud Functions and vLLM — Deploys Llama 3.2 on GKE with vLLM and exposes it through a Gen2 Cloud Function.

Vertex AI Search (7)

• Create a Vertex AI Datastore and Search Engine — Creates a Vertex AI Search datastore, imports GCS PDFs, creates an enterprise search engine, and queries it.
• Defining custom attributes based on URL patterns in Vertex AI Search Website Datastores — Shows how to add URL-pattern custom attributes to a Vertex AI Search website datastore.
• Event-based Triggering of Manual Recrawl for Vertex AI Search Advanced Website Datastores — Automates Vertex AI Search manual recrawl from JSON URL lists uploaded to Cloud Storage.
• Parsing and Chunking in Vertex AI Search: Featuring BYO Capabilities — Retrieves, reviews, exports, and reimports Vertex AI Search parsed and chunked documents with BYOC.
• Query-Level Boosting, Filtering, and Facets for Vertex AI Search Website Datastores — Configures Vertex AI Search website datastore schema, filters, facets, and boosting via REST.
• Recording Real-Time User Events in Vertex AI Search Datastores — Records real-time search and view-item user events for a Vertex AI Search website datastore.
• Q&A Chatbot with Vertex AI Search for summarized website results without advanced indexing — Builds a Q&A flow that searches a Vertex AI Search website data store, fetches the top page, and summarizes it with Gemini.

Vision (1)

• Virtual Try-On: Batch Generation Pipeline — Batch-generates virtual try-on images from person and apparel inputs using Google GenAI SDK.

Related concepts

• Gemini Capabilities · RAG & Grounding · Vision · Embeddings & Vector Search · Prompt Engineering · Agents & ADK · Function Calling & Tools · Evaluation

---

Part of the Generative AI Google Brain · Applied Use Cases - Best Practices