Agent Designer in Gemini Enterprise
In this course, users learn to use Agent Designer within Gemini Enterprise to build and customize no-code agents using prompt design.
0.5 d
Fundamental
GCP200BAGENT
Building Agents for Gemini Enterprise Training
Gemini Enterprise Agent Designer allows you to rapidly transform complex business requirements into autonomous, data-aware workflows. Participants will master flow-builder configuration to create knowledge-grounded agents that tap into internal company data and design powerful multi-agent systems to coordinate specialized tasks across multi-stage projects. This course is a fast-paced, 90% hands-on and demo session, structured around a set of practical use cases called “Plays.” You will deploy web-connected agents on recurring schedules for high-impact deliverables
What you will learn
- Create prompt-based agents.
- Use the flow builder to manually configure knowledge-grounded agents.
- Build an agent orchestrator that delegates tasks to multiple specialized sub-agents.
- Create an autonomous, web-connected agent with a recurring schedule.
- Work on your own agent use case
Prerequisites
- A basic understanding of generative AI and Gemini.
Target audience
- Anyone who wants to learn to build agents for Gemini Enterprise using the Agent Designer.
Training Program
5 modules to master the fundamentals
Objectives
- Construct conversational agents using prompt-based instructions in Agent Designer
- Formulate agent instructions to generate consistent, structured responses
- Implement multi-step routing logic to triage inputs across specialized agent roles
Topics covered
- →Navigate to the Agent Designer and create an agent using a conversational prompt
- →Write effective agent instructions that produce consistent, structured output
- →Test and refine an agent using the Preview tab
- →Create a multi-step agent that triages inputs and routes them between two distinct roles
Objectives
- Design custom agent workflows utilizing the Agent Designer flow builder
- Ground agent responses in uploaded corporate knowledge documents
- Construct a compliance agent to verify content against organizational policies
Topics covered
- →Create an agent using the Agent Designer flow builder
- →Upload a knowledge document to ground an agent’s responses in a specific source
- →Configure starter prompts that guide users to the most common tasks
- →Build a compliance-focused agent that audits content against a policy document
Objectives
- Architect a multi-agent orchestration system with specialized sub-agents
- Configure routing rules to dynamically delegate tasks to appropriate sub-agents
- Evaluate multi-agent workflows end-to-end using realistic business scenarios
Topics covered
- →Design a multi-agent system with a root orchestrator and specialized sub-agents
- →Add and configure sub-agents in the flow builder
- →Write routing logic that delegates tasks to the right agent
- →Test a multi-agent flow end-to-end with realistic input
Objectives
- Integrate the Google Search tool to enable live web grounding for agents
- Configure recurring execution schedules for autonomous agent operations
- Verify and monitor scheduled agent executions via chat preview and history logs
Topics covered
- →Create an agent that uses the Google Search tool to access current web content
- →Configure a recurring execution schedule with a specific prompt
- →Test a scheduled agent before its first automatic run using the Preview function
- →Monitor scheduled agent runs in the chat history
Objectives
- Formulate an actionable agent specification from a real-world business challenge
- Select and implement an optimal agent architecture to resolve custom workflow requirements
- Iteratively test and optimize custom agent instructions for enterprise reliability
Topics covered
- →Translate a real workplace problem into a well-defined agent use case
- →Choose the right agent architecture for your scenario
- →Write effective instructions that make your agent reliable and consistent
- →Test and refine your agent using the Preview tab
Related Trainings
Gemini Enterprise Tools Workshop
The Gemini Enterprise Tools Workshop is designed to equip you with the advanced skills necessary to maximize the full suite of Gemini's built-in tools. Using a realistic case study, participants will learn how to seamlessly integrate web search, manage contextual files, and conduct comprehensive deep research. This course is a fast-paced, 90% hands-on and demo session, structured around a set of practical use cases called "Plays." You will learn how to use advanced prompt engineering techniques and built-in Gemini tools to synthesize complex information and drive data-backed decisions.
0.5 d
Intermediate
Gemini Enterprise Promptathon: Capstone
The Gemini Enterprise Promptathon is an intensive, hands-on workshop where you will apply your skills from the Explore AI for Activation courses to a real-world challenge. Working in teams, you will tackle a use case of your choosing, progressing from an initial idea to a functional prototype. This capstone hands-on event emphasizes collaboration, rapid prototyping, and creative problem-solving using the full suite of Gemini Enterprise tools. At the end of the session, your team will present your solution, showcasing your ability to deliver tangible business value with generative AI.
0.5 d
Advanced
Upcoming sessions
No date suits you?
We regularly organize new sessions. Contact us to find out about upcoming dates or to schedule a session at a date of your choice.
Register for a custom dateQuality Process
SFEIR Institute's commitment: an excellence approach to ensure the quality and success of all our training programs. Learn more about our quality approach
Teaching Methods Used
- Technical Demonstration (Demos) — The instructor performs a task or procedure while students observe.
- Guided Labs — Guided practical exercises on software, hardware, or technical environments.
- Role Play / Simulation — Simulation of a professional interaction (sales, management, support).
Evaluation and Monitoring System
The achievement of training objectives is evaluated at multiple levels to ensure quality:
- Continuous Knowledge Assessment : Verification of knowledge throughout the training via participatory methods (quizzes, practical exercises, case studies) under instructor supervision.
- Progress Measurement : Comparative self-assessment system including an initial diagnostic to determine the starting level, followed by a final evaluation to validate skills development.
- Quality Evaluation : End-of-session satisfaction questionnaire to measure the relevance and effectiveness of the training as perceived by participants.
Frequently Asked Questions
Anyone who wants to build agents for Gemini Enterprise with the Agent Designer, from business analysts to technical profiles. The workshop is hands-on rather than theoretical.
It means the agent answers from your internal company data rather than from general knowledge alone. You configure that grounding manually with the flow builder.
You will be able to create prompt-based agents, configure knowledge-grounded agents with the flow builder, build an orchestrator that delegates to specialized sub-agents, and set up a web-connected agent running on a recurring schedule.
Yes. The last module is a bring-your-own-use-case session where you build an agent for a workflow of your own with the instructor's support.
Four hours, instructor-led by SFEIR Institute, structured as a series of hands-on plays rather than lectures.
Yes. This is an official Google Cloud course delivered by SFEIR Institute, a certified Google Cloud Training Partner and Google Cloud Training Partner of the Year 2025.
Our training organizations SFEIR SAS and SFEIR-Est are Qualiopi certified for training activities. Contact us for a quote.
Train multiple employees
- Volume discounts (multiple seats)
- Private or custom session
- On-site or remote