Generative AI is handy for condensing and simplifying vast amounts of info. Use cases for marketers and business execs include:
- Explaining complicated documents, such as patents.
- Summarizing long narratives into key points and definitions.
- Extracting important sections of ebooks and whitepapers for blogs and promotional materials.
What follows are four gen AI tools to accomplish those tasks. To test, I instructed the tools to analyze a 2023 patent from Google for Search Generative Experience, with three prompts:
- What is this document about?
- How does SGE select external resources in its answers? Do the resources originate from organic search results?
- Define essential terms from the document.
My goals were to evaluate the accuracy of the responses and check for “hallucinating” — inventing info.
ChatGPT can now process uploaded documents, including PDF files. It provided a generic overview of the prompt, “What is this document about?”
But it was the only tool that answered the second question, “Did the resources originate from organic search results?”
According to the patent document, not all documents are selected solely from organic search results. The selection process involves different categories of search result documents:
Query-Responsive Search Result Documents: These are documents obtained in response to the original query submitted by the user.
Related-Query-Responsive Search Result Documents: These documents are derived from searches performed for queries related to the original query.
Recent-Search-Responsive Search Result Documents: These are documents that responded to recent queries, possibly related to the current query or user’s search history.
ChatGPT made up the names of the categories (in bold)! The patent does not use those terms.
So I prompted, “I don’t see these category names in the original document. Did you make them up?”
You are correct, and I apologize for the…
This is only a snippet of a eCommerce Article, please visit the Authors Website and Read the Full Article