liveBook · Manning

Dialogue

As explained in Building Reliable AI Systems

A record of the messages exchanged during a conversation.

Dialogue history records messages exchanged during a conversation. As short-term memory, it preserves session details—such as a customer’s name, problem, and account number—so an agent can respond without asking again. It is typically held in a buffer, list, or dictionary and discarded when the session ends. section 6.2.1

Order tracking

An agent can temporarily store an order ID and use it to retrieve updates during the session. section 6.2.1

class ShortTermMemory:
    def __init__(self):
        self.memory = []

    def add_message(self, message):
        self.memory.append(message)

    def get_memory(self):
        return self.memory

A minimal list-backed store appends messages and returns the session history. section 6.2.1

How Building Reliable AI Systems covers it

How deep it goes
Describes lightweight session storage and gives a simple list-based implementation.
Examples
Uses support-chat details, troubleshooting context, and an order ID to illustrate reuse during a session.
What you can do after
Build it from scratch by appending messages to a list and returning the stored history.
How it connects
Connects dialogue history to short-term memory and distinguishes it from persistent memory retained across sessions.

Also explained in

Compare how 10 books explain dialogue →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Building Reliable AI Systems. The section links point to the parts of the book it draws on.