# Customer Support Agent ### The challenge Many businesses face the challenge of how to handle increasing numbers of customer pre-sale enquiries, on subjects ranging from company opening hours to complex product features. This can be a strain for a first-line customer support team, as the market increasingly demands instant responses, delivered 24/7. ### How it works This is where the Customer Support Agent can help. The agent is trained specifically on your company and its products, resulting in accurate customer replies, without "hallucinating" or making up information. In effect, the Customer Support Agent is like having your own custom ChatGPT chatbot that answers questions based on your own data. Your Customer Support Agent can be deployed over webchat and WhatsApp. Once the AI agent is published, all new incoming messages over the channels you have connected will be assigned automatically to the AI agent, which will respond directly to your customer. ### Key capabilities **Product & pricing questions** - The agent draws on the documents, URLs, and FAQs in your Knowledge Base to respond to detailed questions about what you offer and how much it costs, providing accurate, up-to-date answers. **Feature explanations** - When customers want to understand how something works or what's included, the agent breaks down features in clear, accessible language tailored to the tone and technical level you've configured. **Lead capture & escalation** - The agent doesn't just answer questions - it listens for buying signals. When it detects purchase intent or a request that warrants human attention, it can capture the lead's details and escalate the conversation to your team seamlessly. ### AI-to-human handover If the question is too complex for the AI agent to answer, it's trained to recognise when its answer is not sufficient to keep the customer happy, and it will offer to hand over the chat to a human agent. Alternatively, the customer can just ask to chat with a human agent directly. It's also possible to assign the chat back to the AI again, if required. All chats, whether resolved by the AI Agent or assigned to a human, can be viewed and responded to via the group's team inbox. ### Best suited for Businesses that receive a high volume of pre-sale enquiries across channels like WhatsApp, webchat, or social messaging. Particularly effective for SaaS companies, service businesses, and e-commerce, where customers need product clarity before making a decision. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://converso.gitbook.io/product-documentation/ai-agents/agent-store/customer-support-agent.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.