AI-102 Implement knowledge mining and information extraction

A bank must send each loan file to its internal underwriting scorer during indexing and store the returned grade as a searchable field. Built-in skills cannot provide this grade. What should the team use?

Show answer and explanation

Answer: D

A custom Web API skill lets an enrichment pipeline call an external endpoint for each document and return the result into the enrichment tree. The returned grade can then be mapped to an index field so it is searchable. This is the right extension point when the required logic lives in an internal service rather than in a built-in skill.

Why the other options are wrong

  • A. The semantic ranker reorders results at query time. It does not call an external scorer or write a grade into the index during enrichment.
  • B. A knowledge store saves enrichment output for analytics projections. It does not invoke the underwriting service to produce the grade.
  • C. Entity recognition extracts named entities from text. It cannot reproduce the internal scoring logic that produces the grade.

Keep going. 175 AI-102 questions, answers explained after each one.

Practise this domain

Reviewed November 2026. Spotted a problem with this question? Report it from the practice tool.