Michael Brenndoerfer | Data & AI, Private Equity, Technology

Michael Brenndoerfer

Short-Term Conversation Memory › The Problem: Stateless Interactions

Michael BrenndoerferJuly 1, 20252 min read

AI Agent HandbookAll chapters

Part 6 of 15Memory and Retrieval - How Agents Remember

Chapter 15Short-Term Conversation Memory › The Problem: Stateless Interactions

Reading section 2 of 15 · The Problem: Stateless Interactions · 2 minSection 2 of 15 · 2 min

Section 2 of 15 · 2 min read

Short-Term Conversation Memory › The Problem: Stateless InteractionsOne section · Sections in this chapter2 / 15 ↓

Sections in this chapter15

Let's see what happens without memory. Here's a conversation with our agent:

User: What's the capital of France?
Agent: The capital of France is Paris.

User: What's the population?
Agent: I need more context. What location are you asking about?

The agent answered the first question perfectly. But when you asked a follow-up ("What's the population?"), it had no memory of discussing France. Each interaction is isolated, like talking to someone with amnesia.

This breaks down quickly in real conversations. People naturally ask follow-up questions, refer to previous topics, and build on earlier context. Without memory, your agent can't handle these basic conversational patterns.

Example (Claude Sonnet 4.5)Link Copied

Let's see this in code:

In[3]:

Code

import os
from anthropic import Anthropic

## Using Claude Sonnet 4.5 for its excellent conversational capabilities
client = Anthropic(api_key=os.getenv("ANTHROPIC_API_KEY"))

def ask_without_memory(question: str) -> str:
    """Ask a question without any conversation history."""
    response = client.messages.create(
        model="claude-sonnet-4-5",
        max_tokens=1024,
        messages=[
            {"role": "user", "content": question}
        ]
    )
    return response.content[0].text

## First question
print("Q1:", ask_without_memory("What's the capital of France?"))
## Output: "The capital of France is Paris."

## Follow-up question
print("Q2:", ask_without_memory("What's the population?"))
## Output: "I'd be happy to help with population information, 
## but I need to know which location you're asking about."

Out[3]:

Console

Q1: The capital of France is Paris.

Q2: I'd be happy to help you with population information! Could you please specify which location you're asking about? For example:

- A specific city?
- A country?
- The world?
- Some other area?

Each call to ask_without_memory creates a fresh conversation. The agent has no context from previous questions. This is the default behavior when you don't explicitly manage conversation history.