GOOGLE GEMINI ENTERPRISE — TRACK 3 / 5
Build Production-Grade AI Agents with ADK
COMING SOON
The developer track. Build, orchestrate, deploy, and govern enterprise AI agents with Google's Agent Development Kit (ADK). Aligned with the GEAR program (35 monthly Google Skills credits) and Google Cloud Next '26's 15-component Agent Platform.
Google Cloud Premier Partner
The Bootcamp
Agent Engineering with ADK on Gemini Enterprise
A 3-day developer intensive built around Google's Gemini Enterprise Agent Ready (GEAR) program announced at Cloud Next '26. You'll work in Python / TypeScript / Go / Java with the open-source Agent Development Kit; build multi-agent systems with A2A and MCP protocols; deploy to Vertex AI Agent Engine, Cloud Run, and GKE; and master the 15-component Agent Platform. The capstone is the operational rollout pattern for 20K–50K Vertex AI projects — the exact pattern the inbound EDU client requires.
- Build agents with the Agent Development Kit (Python · TypeScript · Go · Java)
- Implement multi-agent orchestration with Model Context Protocol (MCP) and Agent2Agent (A2A)
- Build apps with Agent Designer / Agent Studio (no-code) and graduate to ADK
- Deploy agents to Vertex AI Agent Engine, Cloud Run, and Google Kubernetes Engine
- Operate the Agent Platform — Identity, Registry, Gateway, Anomaly Detection
- Run Simulation, Evaluation, Observability, and Optimizer at production scale
- Architect a 20K–50K Vertex AI project rollout for large EDU / enterprise tenants
What You Need Before Day 1
Required
- Laptop with internet access (macOS, Windows, or Linux)
- Programming experience in any of Python, TypeScript, Go, Java
- Foundations track (or equivalent Gemini Enterprise familiarity)
Not Required
- Prior agent-development experience
- Google Cloud certification
Bring an idea you'd like to build during the capstone — we'll help you shape it into a deployable agent.
THE CURRICULUM
What You Will Build
Eleven modules covering the full agent lifecycle from foundations to enterprise rollout.
AGENT FOUNDATIONS & GOOGLE AGENT ECOSYSTEM
120 MINAgentic AI vs traditional AI. Agent anatomy — model, tools, memory, system instructions. Reasoning loops (gather → act → verify). Where agents fit in Google Cloud (Vertex AI, Gemini API, ADK, Agent Engine). Mantra — Develop with ADK; Operate with Gemini Enterprise.
ADK — BUILD YOUR FIRST AGENT
120 MINADK languages (Python, TypeScript, Go, Java). Core abstractions — Agents, Tools, Workflow Agents, Memory Bank. Local dev setup; project scaffolding. Tool ecosystem (3rd-party + custom tools). Predictable pipelines vs agent-coordinated routing. Built-in evaluation framework. Deployment surfaces (Local, Agent Runtime, Cloud Run, GKE).
MULTI-AGENT ORCHESTRATION — MCP & A2A
120 MINParent-child agent flows; task delegation patterns. Model Context Protocol (MCP) for secure enterprise system connections. Agent2Agent (A2A) Protocol for multi-agent communication. Workflow Agents controlling work-flow automatically. Session state propagation between agents. Compliance-focused deterministic flows for critical ops.
NO-CODE / LOW-CODE — AGENT DESIGNER & AGENT STUDIO
60 MINVisual workflow builder for non-developers. Pre-built templates via Agent Garden (code modernisation, financial analysis, invoice processing). Direct export from Agent Studio to ADK for deeper customisation. When to choose Agent Studio vs Agent Designer vs ADK.
BUILD YOUR FIRST GEMINI ENTERPRISE APPLICATION (LAB)
90 MINHands-on lab — Cymbal Foods Marketing scenario (Skills #1586). Prepare data, create the GE application, connect data stores (GCS, Drive, Calendar), interact with agents, use the Deep Research agent, focused NotebookLM analysis. Earn the 'Deploy an Agent with ADK' skill badge.
ENHANCING CX WITH AGENTS (CROSS-FUNCTION LAB)
90 MINRAG (Retrieval-Augmented Generation) fundamentals and tooling. RAG in action lab. Search agents — power and limits. Vertex AI Search shopping-experience use case. Build-your-own-agent walk-through. Bridges this track to the CX track.
VERTEX AI POWER TOOLS FOR DEVELOPERS
90 MINVertex AI Studio walkthrough. Gemini API — 2.0 Flash, multimodal reasoning. Model selection by complexity (2.5-flash vs 2.5-pro) for cost / performance trade-off. Hands-on labs designed for student / developer curriculum use. Token budgeting per project; cost tracking at scale.
PRODUCTION DEPLOYMENT — RUNTIME, ENGINE, CLOUD RUN, GKE
90 MINDeployment targets — Vertex AI Agent Engine (managed), Cloud Run (containerised), GKE (full control). Containerising tool-using agents. Agent Runtime — sub-second cold starts. Long-running agent support (multi-day workflows). Bidirectional streaming (WebSocket). Live audio and video via multimodal streaming. Skill badge — Deploy an Agent with ADK challenge.
GOVERN AT ENTERPRISE SCALE
75 MINAgent Identity — cryptographic ID per agent, audit trails. Agent Registry — single source of truth. Agent Gateway — 'air traffic control' for agent-to-tool interactions. Agent Anomaly + Threat Detection — Security Command Center integration. CISO-approved guardrails. Agent Sandbox — hardened execution for model-generated code.
EVAL, OBSERVABILITY & CONTINUOUS IMPROVEMENT
75 MINAgent Simulation — synthetic users + virtualised tools for pre-prod testing. Agent Evaluation — multi-turn autoraters, turnkey dashboards. Agent Observability — execution traces, real-time debugging. Agent Optimizer — automatic failure clustering, refined system-instruction suggestions. KPIs and alert configuration.
OPERATIONAL ROLLOUT AT SCALE — UNIVERSITY PATTERN
90 MINCapstone. Operational rollout pattern for 20K–50K Vertex AI projects. GUI front-end for admin staff (Terraform-backed). Auto-provisioning + offboarding; bulk operations. Budget alerts and auto-terminate; student access revocation. Memory Bank for per-user personalisation. Agent Sandbox for safe student-code execution. Cost attribution per department / faculty / course. Decommissioning at semester end.
Your Instructors
Naveen Kumar
AI/ML Engineer
"I've built AI systems across Zoho, Virtusa, and now SquareShift, from machine learning pipelines to generative AI applications. At RocketOne, I teach you the practical skills to build AI-powered solutions that work in the real world, not just in notebooks."
Specialty
Prem Kumar
AI Architecture Expert
"Anyone can build an AI demo. I teach you how to build the architecture behind systems that scale, because the gap between prototype and production is where most teams get stuck."
Specialty
Clients: Broadcom, Oracle
Himal Rajan
Full Stack & AI Developer
"From React frontends to Python AI backends, I've spent my career building full-stack systems that actually ship, RAG pipelines, autonomous agents, and production APIs that handle real traffic. At RocketOne, I teach you the exact engineering decisions that turn an AI prototype into a system your users can depend on."
Specialty