liveBook · Manning

Prompt suggestion

As explained in The Art of AI Product Development

A prompt suggestion is a proposed example or partial instruction that helps a user formulate an input for an AI system.

A prompt suggestion is a design pattern that nudges users toward correctly formulated questions for an AI system. In a financial analytics chatbot, suggestions can make the first interaction less intimidating without requiring users to know how to prompt. section 2.1.2

Validate prompt suggestions progressively:

  • Test alternative suggestions with employees before exposing them to external users. section 2.1.2
  • Move into controlled external-user settings, then release successful variations in the wild. section 2.1.2
  • Measure usage and satisfaction, and use small sandbox pilots when faster iteration is difficult. section 2.1.2

How The Art of AI Product Development covers it

How deep it goes
Explains the pattern’s purpose and staged validation process, but does not specify interaction designs or implementation details.
Examples
Uses a financial analytics chatbot, employee tests, controlled external-user trials, and in-the-wild measurement as examples.
What it assumes
Assumes an AI chatbot or comparable input experience, while treating effective question formulation as a design problem.
What you can do after
Apply it via staged UX experiments that compare suggestions and measure usage and satisfaction.
How it connects
Connects prompt suggestions with chatbots, templates, user testing, sandbox pilots, usage metrics, and satisfaction measurement.
Cover of The Art of AI Product Development
liveBookmanning.com
Read The Art of AI Product Development on liveBook Get the book at manning.com

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.