The Scenario
You're a researcher at a financial services firm. A colleague left last month, and you've inherited their workflow — part of which involved maintaining a background reading sheet on regulatory topics for the compliance team.
The workbook is supposed to contain the most relevant Wikipedia reference pages on whatever topic compliance is focused on this quarter: "autonomous vehicle liability law." The workbook is empty. Your colleague never built it.
You could search Wikipedia manually. But the topic is technical enough that keyword search returns a mix of directly relevant pages and loosely related ones. What you need is semantic relevance — pages substantively about autonomous vehicles and liability frameworks, not just pages that mention those words.
The bad version:
- Search Wikipedia for "autonomous vehicle." Open the top result. Decide whether it's about liability. Copy the title and URL into the workbook.
- Search "liability law autonomous." Skim. Copy three more. Realize two overlap with the first search.
- Deduplicate. Reorder. Format the columns consistently. You have 10 pages but you're not confident they're the most relevant 10. You need 15.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. Through its Perigon integration, it runs a vector search against Wikipedia and writes the semantically closest pages — title, URL, and snippet — directly into your workbook.
Perform a Perigon semantic Wikipedia search for "autonomous vehicle liability law" and populate my Excel Background Reading sheet with page title, URL, and snippet for the top 15 results.
What You Get
- 15 rows in the Background Reading worksheet, each representing one semantically relevant Wikipedia page.
- Column A: page title. Column B: URL. Column C: snippet or one-line summary.
- Ranked by semantic relevance to your query — not by keyword overlap.
- Ready to share with the compliance team immediately.
What If the Data Is Not Quite Ready
The query should be read from a cell
Read the research query from cell B1 of the Config worksheet. Use Perigon semantic Wikipedia search for that query and write the top 15 results to the Background Reading worksheet with page title, URL, and snippet.
You want fewer results but higher confidence
Use Perigon semantic Wikipedia search for "autonomous vehicle liability law". Return the top 10 results only. Write page title, URL, and snippet to the Background Reading worksheet.
You need to cross-reference against pages already in a previous reading list
Use Perigon semantic Wikipedia search for "autonomous vehicle liability law". Get the top 15 results. For each page, check if the URL already exists in column B of the Previous Reading List worksheet. Write page title, URL, and snippet to the Background Reading worksheet. In column D, mark "new" or "repeat" based on the check.
Pull semantic Wikipedia results, categorize by subtopic, and build a structured index in one pass
Use Perigon semantic Wikipedia search for "autonomous vehicle liability law". Retrieve the top 15 results. Write page title, URL, and snippet to the Background Reading worksheet. In column D, assign each page to one of three subtopic buckets — "vehicle technology", "liability framework", or "regulatory policy" — based on the title and snippet. Count pages per bucket and write the totals to the Summary worksheet.
Ask for the search, categorization, and summary in one prompt.
Try It
Get the 7-day free trial of SheetXAI and open any Excel workbook where you're building a reference library or background reading index, then ask it to run a Perigon Wikipedia semantic search and populate the results. See the full Perigon integration overview or explore building a one-shot research brief using Perigon and Wikipedia.