Citation

As explained in The Art of AI Product Development

A source citation is a link or reference identifying information sources used to produce an AI output.

An AI-generated answer may be easy to read but hard to trace. A citation links to a source used to craft the output, giving users a way to inspect its basis rather than relying on the answer alone. section 10.2.2

Source links are a shortcut to a fuller footprint of how an answer was produced, especially when a single-step LLM generation leaves that process opaque. They help users verify an output; they do not reveal every step behind it. section 10.2.2

Figure 10.22 Providing transparency into the original sources is a core strategic differentiator for Perplexity.ai. Other AI systems, especially RAG setups, can also benefit from this UX pattern.

Perplexity.ai illustrates how showing original sources can become a visible part of an AI product’s experience. The same pattern can benefit RAG systems. section 10.2.2

How The Art of AI Product Development covers it

How deep it goes

Defines the UX pattern and contrasts it with fuller process footprints, without detailing citation generation or validation.

Examples

Uses Perplexity.ai’s display of original sources as the concrete product example.

What you can do after

Evaluate/understand citations as a way for users to check the sources behind generated answers.

How it connects

Connects citations to transparency, process footprints, verification, and retrieval-augmented generation.

liveBookmanning.com

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

Related concepts

• Copilotproduced by · Copilot is a Microsoft-branded family of AI assistant products that provide task-oriented assistance within software and services, including conversational, content-generation, and coding capabilities.
• ChatGPTused by · ChatGPT is OpenAI's conversational AI service, which enables users to interact with AI models through prompts and receive generated responses and other content.
• groundingused by · Grounding is the practice of anchoring or constraining an AI system’s outputs with relevant information, context, or evidence.
• grounded answerproduces · A grounded answer is a response whose claims are supported by relevant supplied or retrieved source context.
• retrieval-augmented generationproduced by · 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.
• web searchproduced by · Web search is the retrieval of information from publicly accessible World Wide Web pages or indexes in response to a query.

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.