/google-cloud-solution-agentic-ai-bidirectional-streaming

name: google-cloud-solution-agentic-ai-bidirectional-streaming
metadata:
  version: "1.0.2"
  category: MultiProductSolutions
description: >-
  Guides agents to interactively discover customer requirements
  for live, bidirectional multi-agent AI systems that process continuous streams
  of multimodal data for real-time technical guidance and safety monitoring.
  Generates a custom Google Cloud solution that uses opinionated best practices
  and architecture guidance. Use when users need agentic assistance to design
  and create a multi-product solution in the cloud for live bidirectional
  multimodal streaming workloads. Don't use for simple text-based chat
  applications or workloads without real-time streaming requirements.

Live bidirectional multimodal streaming agentic AI solution

This skill guides agents through the workflow to design and implement a tailored multi-product solution in the cloud for a live, bidirectional multimodal streaming workload, use case, or requirement.

Attribution

**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you MUST read and follow the instructions in [Usage Attribution](references/attribution.md).

Workflow

The solution design and implementation workflow consists of the following phases:

• **Phase 1: Requirements discovery and analysis**: Analyze the workload's

requirements, constraints, dependencies, and current state.

• **Phase 2: Solution design**: Build a technology stack, architecture, and

deployment configuration for the workload based on Google Cloud design best practices and recommendations.

• **Phase 3: Implementation plan**: Generate automation and instructions to

deploy the solution.

• **Phase 4: Solution validation**: Validate that the deployment meets the

requirements of the workload.

Phase 1: Requirements discovery and analysis

• [ ] **Step 1: Discover requirements**: Understand the functional and

non-functional requirements, business goals, and current state (if any) of the workload, including its architecture, dependencies, and constraints. Use the following questions to guide the requirements discovery process:

• What are the primary input modalities (audio, video, or text) and

what is the target latency for real-time, narrated feedback?

• Do you require real-time safety monitoring, hazard detection, or visual

inspection? If so, then what specific safety hazards, operational risks, or incorrect steps need to be monitored and detected in the video stream?

• What existing systems, knowledge bases, product documentation, or

schematic repositories must the AI agents access for grounded guidance?

• What are the client-side device constraints and network limitations?

• [ ] **Step 2: Identify components**: Based on the requirements analysis,

identify the components of the workload and their relationships. Also identify any cross-cloud components, hybrid components, or on-prem components that the solution needs to integrate with.

• [ ] **Step 3: Generate component decomposition**: Generate a technical

decomposition of the components of the workload. The technical decomposition must break down the solution into logical components.

• [ ] **Step 4: Ask for confirmation**: Ask the user to confirm whether the

generated technical decomposition matches their workload requirements.

• [ ] **Step 5: Iterate**: If the user requests changes, then generate an

updated technical decomposition, and ask the user to confirm the changes. Continue iterating until the user confirms the technical decomposition.

Phase 2: Solution design

• [ ] **Step 1: Retrieve relevant Google Cloud documentation**:
• [Enable live bidirectional multimodal streaming](https://docs.cloud.google.com/architecture/agentic-ai-bidirectional-multimodal-streaming.md.txt)
• [Multi-agent AI system in Google Cloud](https://docs.cloud.google.com/architecture/multiagent-ai-system.md.txt)
• [Choose your agentic AI architecture components](https://docs.cloud.google.com/architecture/choose-agentic-ai-architecture-components.md.txt)
• [Multi-agent private networking patterns in Google Cloud](https://docs.cloud.google.com/architecture/multi-agent-private-networking-patterns.md.txt)

*Important*: Use the content that you retrieve from Google Cloud documentation to ground the guidance that you generate in the remaining steps of this phase.

• [ ] **Step 2: Map components to Google Cloud products**: For each component in

the confirmed technical decomposition and agentic design pattern, identify the appropriate Google Cloud products and features, based on the guidelines in [references/product-mapping.md](references/product-mapping.md).

• [ ] **Step 3: Create architecture diagram**: Generate an architecture diagram

in Mermaid format: https://github.com/mermaid-js/mermaid.

• [ ] **Step 4: Generate design recommendations**: Generate design guidance

based on the guidelines in [references/design-recommendations.md](references/design-recommendations.md).

• [ ] **Step 5: Draft solution architecture**: Compile the requirements, technical

decomposition, product mapping, architecture diagram, and design recommendations into a single Markdown file named `solution-architecture-guide.md`, based on the template in [assets/output-template.md](assets/output-template.md).

• [ ] **Step 6: Request review**: Present the generated solution architecture to

the user and request their feedback or approval.

• [ ] **Step 7: Iterate**: If the user requests changes, generate an updated

solution architecture and repeat steps 2-6 until the user approves the solution architecture.

Phase 3: Implementation plan

• [ ] **Step 1: Retrieve relevant implementation resources**:
• [Host AI agents on Cloud Run](https://docs.cloud.google.com/run/docs/ai-agents.md.txt)
• [Triggering Cloud Run with WebSockets](https://docs.cloud.google.com/run