Claude with Amazon Bedrock

How Chat Applications Work

Imagine you’re building a web app with a simple chat interface. A user types “Define quantum computing” and clicks send. Here’s what actually happens:

The user sees a clean interface, but there’s a whole system working behind the scenes to generate that response.

The Request Flow

When a user submits text, here’s the journey that message takes:

User submits their message through your web interface
Your server receives the request containing that text
Your server uses the Bedrock client to make a request to AWS Bedrock
The request includes the user message and a model ID (like Claude Haiku or Claude Sonnet)
The chosen model processes the request and generates text
AWS Bedrock sends back an assistant message containing the generated response
Your server forwards this response back to the user’s browser

			
import boto3
client = boto3.client("bedrock-runtime", region_name="us-west-2")
model_id = "us.anthropic.claude-sonnet-4-20250514-v1:0"
def add_user_message(messages, text):
    user_message = {"role": "user", "content": [{"text": text}]}
    messages.append(user_message)
def add_assistant_message(messages, text):
    assistant_message = {"role": "assistant", "content": [{"text": text}]}
    messages.append(assistant_message)
def chat(messages):
    response = client.converse(modelId=model_id, messages=messages)
    return response["output"]["message"]["content"][0]["text"]
# Make a starting list of messages
messages = []
# Add in the initial user question of "whats 1+1?"
add_user_message(messages, "Whats 1+1?")
# Pass the list of messages into chat to get an answer
answer = chat(messages)
# Take the answer and add it as an assistant message into our list
add_assistant_message(messages, answer)
# Add in the user's followup question
add_user_message(messages, "And 3 more added to that?")
# Call chat again with the list of messages to get a final answer
answer = chat(messages)
answer
# Make an initial list of messages
messages = []
# Use a 'while True' loop to run the chatbot forever
while True:
    # Get user input
    user_input = input("> ")
    print(f"> {user_input}")
    # Add user's input to list of messages
    add_user_message(messages, user_input)
    # Send list of messages to the API
    text = chat(messages)
    # Add generated text to list of messages
    add_assistant_message(messages, text)
    # Print the generated text
    print(text)

		