Grokking the AI System Design Interview
Vote

0% completed

​

Design AI-Powered Search

Frame the Problem: Adding Seconds to a Millisecond System

"Add AI answers to our search engine" is the Google AI Overviews, Bing, and Perplexity question.

Behind the GenAI description, it is really an integration problem.

For this example, assume the existing search system targets 300 ms responses at 10,000 queries per second (QPS). Specify the latency percentile and whether this is peak or sustained load.

Add generated answers without making core search slower or less reliable. Generation adds latency and cost, so it should be optional.

.....

.....

.....

Like the course? Get enrolled and start learning!

Reading Progress

0%

Vote for new content