Build a Customer Support Chatbot with Claude API

What Makes a Good Customer Support Chatbot?

A good customer support chatbot is built on three things: a well-structured knowledge base it can actually query, a system prompt that constrains its behaviour and sets its personality, and an escalation path that routes genuinely frustrated users to a human agent. Claude's conversational ability handles the language — your design handles the reliability.

Customer support chatbots have a well-earned poor reputation. They fail to understand questions, give irrelevant answers from a FAQ list, and ultimately frustrate customers into demanding a human agent. The difference between a bad support bot and a useful one is not the technology — it is the design of the knowledge base, the system prompt, and the escalation logic.

Claude's conversational ability, combined with a well-structured knowledge base and clear behavioural instructions, produces a support bot that genuinely helps. This project builds a complete customer support chatbot with a static knowledge base, multi-turn conversation management, prompt caching for cost efficiency, and a clear escalation path to human support.

What We Are Building

The chatbot handles these core responsibilities:

1. Answers questions from a company knowledge base — products, policies, account management, troubleshooting
2. Maintains conversation context across multiple turns — no need for users to repeat themselves
3. Recognises when to escalate — complex complaints, billing disputes, and repeated-failure scenarios get handed to a human
4. Handles out-of-scope questions gracefully — redirects rather than guessing or confabulating

Prerequisites

• Python 3.9 or later
• pip install anthropic
• An Anthropic API key set as ANTHROPIC_API_KEY

The Knowledge Base

The knowledge base is the most important component of a support bot. Claude should answer only from this content — not from its general training knowledge about your industry. Define it clearly in your system prompt.

The System Prompt

The Complete Chatbot

Extending the Project

• FastAPI endpoint: Wrap in an API server so any frontend (React, Vue, or a third-party chat widget) can connect to it
• Session storage: Store conversation history in Redis or PostgreSQL keyed by session ID to support concurrent users and persistent sessions
• Dynamic knowledge base: Load the knowledge base from a database or CMS so it can be updated without redeploying the application
• WebSocket streaming: Use the Claude streaming API to start showing the response character by character, reducing perceived latency for users
• Analytics: Log every conversation with metadata (escalation rate, topic classification, resolution status) to identify knowledge gaps

Summary

A well-designed support chatbot has three success factors: a high-quality knowledge base, clear behavioural boundaries, and a reliable escalation path. Claude handles the conversational intelligence — you provide the domain knowledge and the rules.

• Use cache_control on the system prompt to reduce costs at scale
• Maintain full conversation history so Claude has context for follow-up questions
• Define explicit escalation triggers rather than relying on Claude to judge when to escalate
• Use a cheaper model (Haiku) for internal tasks like summary generation

Next project: Project: Build an Automated Meeting Notes Summariser.

For cost optimisation on high-traffic chatbots, see Claude Prompt Caching Guide — prompt caching on the knowledge base system prompt reduces costs by up to 90% for returning users. For RAG-powered chatbots that query large document sets, see Claude RAG: Retrieval Augmented Generation.

External Resources

• Anthropic Prompt Caching documentation — how to reduce costs by up to 90% on repeated system prompts.
• Anthropic conversation memory patterns — official guidance on managing multi-turn conversation history at scale.

This post is part of the Anthropic AI Tutorial Series. Previous post: Project: Build a Smart CV / Resume Analyser with Claude.