Build Agents with CX Agent Studio (BACXAS) – Outline

Detailed Course Outline

Module 1 - Introduction to CX Agent Studio

Topics:

  • Then and now.
  • AI agents and conversational AI solutions.
  • Gemini Enterprise for Customer Experience (CX).
  • CX Agents Studio overview.

Objectives:

  • Refresh your knowledge about AI agents on Google Cloud and CX Agent Studio.
  • Create production-ready agents in CX Agent Studio.

Activities:

  • Lab: Create CX agents ready for production.

Module 2 - Build CX agents

Topics:

  • Product demonstration.
  • Build and refine multi-agent architecture.
  • Hybrid versus deterministic agents.
  • Make your CX agents enterprise ready.

Objectives:

  • Design multi-agent architectures to manage complexity.
  • Apply best practices for instructions.
  • Implement deterministic logic.
  • Configure enterprise-ready features.

Activities:

  • Lab: Use CX Agent Studio memory and deterministic capabilities.

Module 3 - Programmatic management and voice agents

Topics:

  • Programmatic access to CX Agent Studio.
  • Evolution of audio in AI Agents.

Objectives:

  • Build agents programmatically.
  • Configure and troubleshoot Native Audio voice agents.

Activities:

  • Lab: Configure and troubleshoot voice-based agents in CX Agent Studio.

Module 4 - Extend CX Agents with Agent Search data stores

Topics:

  • Introduction to Agent Search and data store agents.
  • Core capabilities and technical advantages of data store agents.
  • Use cases for data store agents,
  • Phases of data store agent implementation.
  • Create a data store agent implementation.
  • Create a data store in CX Agent Studio
  • Connection and configuration.
  • Common search configurations.
  • Common issues and troubleshooting.

Objectives:

  • Differentiate between data store types.
  • Create a data store.
  • Leverage data stores and connectors.

Activities:

  • Lab: Leverage data store and connectors in your CX Agent Studio.

Module 5 - Evaluate and configure CX agents

Topics:

  • Foundations and methods of CX Agent evaluation.
  • Test case development and metrics.
  • Advanced tuning and runs.

Objectives:

  • Align agent responses with defined company rules.
  • Configure guardrails to protect your CX agent.
  • Set up Memory for a CX agent.
  • Implement custom webhooks.

Activities:

  • Lab: Evaluate CX Agent Studio and implement the Quality Hill Climbing process.
  • Lab: Use CX Agent Studio memory and deterministic capabilities.

Module 6 - CX Agent Studio integrations

Topics:

  • Integrate CX agents with first- and third-party providers.
  • Digital channel integrations.
  • Third-party telephony integration.
  • Human escalation to third-party services.
  • Human escalation to Gemini Enterprise for CX.
  • Integration with Agent Assist.
  • Gemini Enterprise for CX integration through the API.

Objectives:

  • Deploy the CX agent to various digital channels.
  • Escalate to human agents using Google Cloud CCaaS and Gemini Enterprise for Customer Experience.
  • Integrate with third party telephony services.

Activities:

  • Lab: Deploy agents to the web and third party channels from CX Agent Studio.

Module 7 - Essentials for a successful launch

Topics:

  • Strategic alignment and planning.
  • Success metrics and visibility.
  • Launch execution and technical readiness.
  • Trust, safety and global readiness.

Objectives:

  • Outline the industry best practices for a successful launch.
  • Recall available compliance languages.