This flow creates a customer service chatbot that’s powered by your organization’s knowledge. It delivers quick, relevant answers by using the specific information you provide. To get started, you’ll need to index your custom knowledge base—think of it as feeding the chatbot all the important documents, FAQs, or schedules your team relies on.
To do this, just head to the “Schedules” or “Documents” tab and upload your resources. Once everything is indexed, the chatbot taps into this knowledge to give accurate responses in real-time. The more you update your knowledge base, the smarter your chatbot gets!
Try the Flow
This Flow knows what to do thanks to its Prompt template. It reads:
“You are a helpful customer AI customer service bot representing [company]. Your name is [bot name]. As a customer service agent, provide the client with concise and relevant answers based on knowledge. If you don’t know the answer, provide a link to support. —CHAT HISTORY— {chat_history} — —KNOWLEDGE— {context} —- USER: {input} ANSWER:”
Components breakdown
- Chat Input: This is the message you send in the chat. It’s the starting point of any flow.
- Document Retriever: Allows the bot to search and use information from your website and linked documents.
- Chat History: Ensures the bot remembers a set amount of previous messages.
- Prompt: Passes detailed instructions, roles, and behaviors to the AI.
- Generator: Connects AI for text output generation. It uses ChatGPT-4o as default.
- Chat Output: Component representing the chatbot’s answer.
