AI Agent for First-Line Customer Support

Automating 24/7 customer query handling with a conversational agent based on Vertex AI Agent Builder and Vertex AI Search.

Client and Business Context

This project was implemented for a large technology company in the AdTech industry. The company needed to streamline and automate its customer support process, particularly for handling frequently asked questions.

Challenge: Scalable 24/7 Customer Support

The main challenge was providing 24/7 customer support directly within the company's product, utilizing existing HubSpot Chatflows. Intelligent query routing was crucial – automatically answering standard questions about pricing, documentation, integrations, and churn, while efficiently redirecting more complex or specific cases to the live support team. The system needed to be scalable and capable of processing information from the company's extensive knowledge base.

  • Handling customer inquiries 24/7.
  • Integration with the existing HubSpot Chatflows system.
  • Automated responses for questions regarding pricing, documentation, integrations, and churn.
  • Intelligent routing of conversations to live support.
  • Need to leverage an extensive internal knowledge base (documentation, FAQ).
  • Ensuring data security and verifying personal data in queries.
  • Monitoring performance and conversation topics.
Architecture diagram of the AI Agent based on Vertex AI

General solution architecture utilizing Vertex AI Agent Builder, Vertex AI Search, and external integrations.

Solution: AI Agent in Vertex AI Agent Builder with RAG

In response to the client's challenges, I designed and implemented an advanced conversational AI agent serving as the first line of support. The solution is based on:

  • Vertex AI Agent Builder: Google Cloud platform for creating and managing AI agents. A Playbook-based architecture was used, allowing precise definition of conversation flows, business logic, and tool integrations for different query types (e.g., separate Playbooks for pricing, documentation).
  • Vertex AI Search: Employed as a scalable RAG (Retrieval-Augmented Generation) system. This enabled the agent to use the client's extensive, unstructured knowledge base (documentation, FAQ) to generate accurate and up-to-date answers.
  • Make.com (Middleware): Automation platform used as a middleware layer to integrate the AI agent with HubSpot Chatflows and other client systems (e.g., CRM, notification systems). Make.com also handles the logic for retrieving current prices and logging conversations.
  • Custom Functionalities:
    • Personal Data Verification: Mechanism to identify and block the processing of sensitive data in queries.
    • Question Categorization and Routing: The main Playbook ("Customer Help Center") analyzes and categorizes the query, then routes it to the appropriate task Playbook (e.g., "Pricing Center," "Documentation Center").
    • User Context from HubSpot: Fetching user data (pricing plan, assigned Account Manager) to personalize responses.
    • Multi-language Support: Automatic translation of queries into English (for RAG) and responses back into the user's language.
    • Team Notifications: Automatic alerts for Account Managers or the Customer Success team for specific queries (e.g., regarding churn).
    • Real-time Pricing: A dedicated Tool (Make.com webhook) providing the agent with current pricing data fetched from the website.
    • Enhanced Logging: An additional Tool (Make.com webhook) saving detailed information about the conversation flow (Playbook used, language) for analytics and debugging purposes.
Example of Playbook configuration in Vertex AI Agent Builder

Playbook configuration in Vertex AI Agent Builder, defining conversation steps, tools used, and parameters.

Make.com integration diagram connecting HubSpot, AI Agent, and logging systems

Make.com scenario acting as middleware, integrating HubSpot Chatflow with the AI Agent API and handling additional functions (logging, price fetching).

Key Benefits for the Client

  • 24/7 Support Availability: Instant responses to customer inquiries at any time.
  • Reduced Response Time: Significant acceleration in answering common questions.
  • Lowered Support Team Workload: Automation of repetitive queries allows the team to focus on more complex issues.
  • High-Quality Answers: Use of RAG (Vertex AI Search) ensures responses are based on current company documentation.
  • Scalability: The solution easily scales with the increasing number of queries and knowledge base size.
  • Personalization: Consideration of user context (plan, AM) in responses.
  • Proactive Notifications: Alerts for relevant teams (AM, CS) at key customer interaction moments.
  • Multilingual Capability: Serving customers in their preferred language.
  • Data Insights: Detailed conversation logging enables analysis and continuous agent improvement.

Frequently Asked Questions (FAQ)

Implementation time depends on the complexity of the required conversation flows (Playbooks), the number and type of integrations (Tools), the volume and structure of the knowledge base (for Vertex AI Search), and specific client requirements. A basic implementation handling a few main topics might take 2 to 4 weeks, while more advanced projects with numerous integrations could take longer. The process includes needs analysis, architecture design, Vertex AI configuration, Make.com scenario creation, training, and testing.

Maintenance costs primarily consist of fees for Google Cloud services (Vertex AI Agent Builder, Vertex AI Search) and the Make.com platform. Vertex AI fees depend on the number of processed queries and resource usage (e.g., RAG). Make.com offers free and paid plans based on the number of operations and data transfer. Costs are generally flexible and scale with usage. Compared to the costs of maintaining a 24/7 support team, an AI solution is often more cost-effective, especially with a high volume of repetitive queries.

Vertex AI Agent Builder provides a graphical interface that simplifies managing Playbooks and configuring the agent without requiring deep programming or AI knowledge. Basic management of the knowledge base content (for RAG) also doesn't require specialized skills. However, designing complex conversation flows, configuring advanced tools, or optimizing prompts might require some technical expertise or expert support.

Thanks to the architecture with automatic translation, the agent can handle queries in multiple languages. The query is translated into English to search the knowledge base, and the response is then translated back into the user's original language. This allows for effective support of global customers while maintaining a single, primary knowledge base.

Standard HubSpot Chatflows rely on predefined decision trees or simple keyword-based bots. An agent based on Vertex AI Agent Builder uses advanced language models (LLMs) and a Playbook architecture, enabling more natural understanding of user intent, flexible conversation management, and execution of complex tasks. Integration with Vertex AI Search (RAG) allows dynamic use of an extensive knowledge base, which standard Chatflows do not offer. Additionally, custom integrations (Tools) and logic implemented in Make.com provide significantly greater automation and personalization capabilities.

The agent utilizes the RAG (Retrieval-Augmented Generation) mechanism based on Vertex AI Search. This means its knowledge primarily comes from the provided data sources (documentation, FAQs, websites). Updating the agent's knowledge involves updating these data sources. The underlying language models (LLMs) are managed by Google Cloud. Additionally, analyzing conversation logs helps identify areas for improvement in Playbook configuration, prompts, or conversation examples, enabling continuous refinement of the agent's performance.

Yes. By leveraging Vertex AI Agent Builder, which supports defining custom API-based tools, and the flexibility of the Make.com platform as middleware, the agent can be integrated with virtually any system that has an API. This can include CRM systems, databases, e-commerce platforms, project management systems, internal communication tools (like Slack), and many others.

Interested in Implementing an AI Agent
in Your Company?

If you want to automate customer service, provide 24/7 support, reduce your team's workload, or leverage AI potential to improve customer experiences – contact me. I'll gladly analyze your needs and propose a tailored solution based on Vertex AI, Make.com, and other technologies.

Let's Talk About Your AI Project