Users frequently misspell product names causing intent match failures. Which feature should the developer enable?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Todd Lammle: 'Imagine you're building a chatbot and this exact situation comes up — spell correction is your go-to move. Spell correction automatically fixes input typos before NLU classification; improving match accuracy. This is a classic Domain 2: Design and Extend Conversations concept you'll want locked in before exam day.'
Full explanation below image
Full Explanation
Spell correction automatically fixes input typos before NLU classification; improving match accuracy. Entity synonyms recognize alternate valid terms but do not fix misspellings. Pattern entities match structured formats. Adjusting confidence thresholds changes what scores are accepted but does not correct the underlying spelling errors. The correct answer, "Spell correction", directly satisfies the scenario because it aligns with watsonx Assistant's design principles and the specific capability being tested. The incorrect options ("Entity synonyms", "Pattern entities", "Confidence thresholds") may appear relevant but each misses a key requirement or introduces a step that is either unnecessary or belongs to a different workflow. Mastering the distinction between these approaches is essential for effective watsonx Assistant implementations and is a core focus of the Domain 2: Design and Extend Conversations section of the certification exam.