Wirewalk Instituteof AI
ven-240 Intermediate Waitlist

Google Vertex AI and the Gemini API

For developers and cloud architects who need to build on Gemini through the Gemini Developer API and Google Cloud's Gemini Enterprise Agent Platform (formerly Vertex AI).

The curriculum is being prepared and reviewed. Enrollment is not open yet.

About this course

Google sells Gemini through two front doors that share a model family but differ in authentication, quotas, data terms and surrounding services. The Gemini Developer API (keys from Google AI Studio) is the fastest path to a prototype; Google Cloud's enterprise platform, called Vertex AI until Google Cloud Next in April 2026 and now Gemini Enterprise Agent Platform, adds IAM, VPC Service Controls, regional data residency, Model Garden, provisioned throughput and managed agent hosting. Many docs, SDK parameters and console labels still say Vertex AI, so this course teaches both names.

You will use the Google Gen AI SDK against both endpoints, compare the legacy generateContent interface with the Interactions API that Google made generally available in June 2026 and now recommends for new projects (and the features, such as batch and explicit caching, that still require generateContent), and control thinking, multimodal inputs and structured output. You will ground answers in Google Search, URL context and your own data, lower cost with implicit and explicit context caching and batch jobs, and size quotas and provisioned throughput. The agent modules cover the Agent Development Kit, deployment to Agent Runtime (formerly Agent Engine) and the Live API for real-time voice. The course ends with Model Garden partner and open models, Gen AI evals, and the security controls regulated organizations ask about first. Facts are as of October 2026.

What you will be able to do

  • Decide between the Gemini Developer API and Gemini Enterprise Agent Platform for a workload based on auth, data terms, quotas and residency
  • Call Gemini with the Google Gen AI SDK using thinking controls, multimodal inputs, response schemas and function calling
  • Explain how the Interactions API differs from generateContent and decide when a project should adopt it or stay on generateContent
  • Ground responses with Google Search, URL context and enterprise retrieval, and verify the returned grounding metadata
  • Reduce cost and latency with context caching, batch jobs and provisioned throughput, and compute the trade-offs
  • Build an agent with the Agent Development Kit and deploy it to Agent Runtime with appropriate IAM
  • Apply VPC Service Controls, CMEK and regional endpoints to meet data-protection requirements

Syllabus

6 modules · 18 lessons · about 12 hours

Module 1: Two Doors to Gemini

How the developer API and the enterprise platform relate, and how to authenticate to each.
3 lessons
  1. Gemini Developer API vs Gemini Enterprise Agent Platform (Formerly Vertex AI)
  2. The Google Gen AI SDK: One Client for Both Endpoints
  3. Projects, IAM Roles, Service Accounts and API Keys

Module 2: Calling Gemini Well

Request interfaces, reasoning controls, multimodal input and structured output.
3 lessons
  1. generateContent vs the Interactions API: State, Background Runs, Feature Gaps and Migration
  2. Thinking Levels, Multimodal Inputs and Media Resolution
  3. Response Schemas, Function Calling and Automatic Function Calling in the SDK

Module 3: Grounding and Retrieval

Tie answers to the web and to your own documents with traceable sources.
3 lessons
  1. Grounding with Google Search and URL Context
  2. File Search in the Gemini API for Managed Document Retrieval
  3. RAG Engine, Agent Search (Formerly Vertex AI Search) and Vector Search on Google Cloud

Module 4: Cost, Quotas and Scale

The levers that decide your bill and your throughput ceiling.
3 lessons
  1. Implicit and Explicit Context Caching
  2. Batch Jobs for Large Offline Workloads
  3. Dynamic Shared Quota, Provisioned Throughput and Regional vs Global Endpoints

Module 5: Agents and Real-Time Apps

Google's agent toolkit, its managed runtime and low-latency voice.
3 lessons
  1. Agent Development Kit: Agents, Tools, Sessions and Multi-Agent Composition
  2. Deploying ADK Agents to Agent Runtime (Formerly Agent Engine)
  3. The Live API for Real-Time Voice and Video Sessions

Module 6: Enterprise Operations

Beyond Gemini: partner models, evaluation and security controls.
3 lessons
  1. Model Garden: Partner Models such as Claude and Open Models such as Gemma and Llama
  2. Gen AI Evals (Formerly the Gen AI Evaluation Service) for Comparing Prompts and Models
  3. VPC Service Controls, CMEK, Data Residency and Logging Settings

Exam and certificate

The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by Google (Gemini API, Gemini Enterprise Agent Platform / Vertex AI, AI Studio, ADK), Anthropic, or Meta (Llama). Product and company names are trademarks of their respective owners.

More in AI Models and Vendors

All 22 courses in this track
ven-001 Free intro Available

Your First Hour with ChatGPT, Claude and Gemini

A hands-on hour with ChatGPT, Claude and Gemini, told through one small business racing a deadline. Set up an account with a privacy setting you chose, decide what never goes into a personal account, write prompts that produce usable drafts, use files and web search, catch confident mistakes before they go out, and pick the assistant that fits how you work.

1 h · 7 lessons Free intro
ven-110 Basic Available

ChatGPT and the OpenAI Platform for Professionals

A practical, current tour of ChatGPT as a professional tool: choosing a plan and model, prompting well, analyzing files, researching with citations, using images and voice, organizing work in projects and memory, connecting apps and plugins, delegating multi-step work to ChatGPT Work, and knowing which admin and privacy controls matter. Ends with clear guidance on moving a workflow to the OpenAI API.

8 h · 15 lessons See price at checkout
ven-120 Basic Available

Claude for Professionals

Learn Claude by solving one firm's real problem: getting through renewal season with too few analysts and without putting client data in the wrong place. Each module compares the approaches professionals actually choose between, shows a realistic failure and its fix, and ends with a Decision Lab where you make the call under pressure.

12 h · 15 lessons See price at checkout