PROFESSIONAL-DATA-ENGINEER Question #253: Real Exam Question with Answer & Explanation

Question

You work for a large financial institution that is planning to use Dialogflow to create a chatbot for the company's mobile app. You have reviewed old chat logs and lagged each conversation for intent based on each customer's stated intention for contacting customer service. About 70% of customer requests are simple requests that are solved within 10 intents. The remaining 30% of inquiries require much longer, more complicated requests. Which intents should you automate first?

Options

• AAutomate the 10 intents that cover 70% of the requests so that live agents can handle more complicated requests
• BAutomate the more complicated requests first because those require more of the agents' time
• CAutomate a blend of the shortest and longest intents to be representative of all intents
• DAutomate intents in places where common words such as "payment" appear only once so the software isn't confused

Explanation

Automating the 10 intents covering 70% of requests delivers the highest immediate ROI - you deflect the majority of volume from live agents with minimal development effort, freeing those agents to focus on the complex 30% where human judgment genuinely adds value. Option B is backwards: complex intents are harder to automate reliably and would delay any real-world impact while agents continue handling the bulk of simple requests. Option C sounds balanced but is a poor strategy - "representative sampling" ignores the volume reality and spreads effort inefficiently across low-impact cases. Option D is nonsensical as a deployment strategy; word frequency is a consideration during NLU training, not a criterion for deciding which intents to automate first.

Memory tip: Think "80/20 rule mindset" - always automate high-volume, low-complexity intents first to maximize coverage with minimum risk. If 10 intents cover 70% of traffic, that's your quick win.

No community discussion yet for this question.