Compound AI system

As explained in The Art of AI Product Development

A compound AI system is an application architecture that combines multiple models with tools, databases, or other computational components.

A compound AI system combines multiple models with tools, databases, and sometimes human oversight to deliver an application outcome. It is more than a single model: components may classify inputs, generate text, transform requests into structured SQL, retrieve data, or route ambiguous cases to people. section 1.3.2

Conversational financial dashboard

A conversational add-on can turn a user request into a structured SQL query, retrieve the necessary database data, and route especially complex or ambiguous requests to a human agent. The surrounding interface must also explain limitations, manage errors, and collect feedback. section 1.3.2

Figure 1.3 Mental model of a conversational assistant for financial data

Use the mental model to trace how a conversational assistant connects user requests, AI processing, data retrieval, and the interface. section 1.3.2

How The Art of AI Product Development covers it

How deep it goes

Defines component roles and oversight needs, but stops short of implementation internals.

Examples

Uses a conversational financial dashboard that transforms requests into SQL and escalates ambiguous cases.

What it assumes

Assumes basic AI awareness while requiring attention to models, data, interfaces, and delivery risks.

What you can do after

Evaluate architectures and identify technologies needed to build trustworthy AI-driven applications.

How it connects

Connects large language models, few-shot prompting, SQL, databases, human oversight, and user experience.

liveBookmanning.com

Read The Art of AI Product Development on liveBook Get the book at manning.com

Related concepts

• retrieval-augmented generationincludes · Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
• AI agentincludes · An AI agent is a computational system that uses artificial intelligence to interpret information, select actions, and pursue goals through interaction with an environment.
• objective functionconfigured by · An objective function assigns values to candidate solutions, predictions, or parameter settings according to a criterion to be minimized or maximized.

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