flâneur — a map of the web's best reading

People + AI Research - Patterns

pair.withgoogle.com · saved by 1 readers

Our design patterns highlight key design opportunities for AI products. They’re organized around common questions in the product development process to help you find what you need. 5 patterns Before you start building with AI, make sure the product or feature that you have in mind requires AI, or would be enhanced by it. AI is well-suited for applications like: A rule or heuristic-based solution may be better when: See the User Needs chapter for more on when to use (or not) AI. Aim for Use AI when the predictive system can create a valuable personalized experience that couldn’t exist without it. Avoid Don’t use AI just because you can. Heuristics or manual control can often create better experiences. Here, using music preferences to suggest workouts will likely lead to a worse experience than letting people manually choose workouts. Because AI systems are probabilistic, your system will probably give an incorrect or unexpected output at some point. This makes it critical that you help

Our design patterns highlight key design opportunities for AI products. They’re organized around common questions in the product development process to help you find what you need. 5 patterns Before you start building with AI, make sure the product or feature that you have in mind requires AI, or would be enhanced by it. AI is well-suited for applications like: A rule or heuristic-based solution may be better when: See the User Needs chapter for more on when to use (or not) AI. Aim for Use AI when the predictive system can create a valuable personalized experience that couldn’t exist without i

Explore this link on the map →