Score trade show exhibitors against your customer profile

An n8n workflow scraped exhibitor lists, checked each company site, and wrote a fit score and note into Google Sheets.

Done with n8n· Intermediate

What they did
A developer connected Bright Data to pull exhibitor names, booth details, short descriptions, and links from a trade show listing, then used code to clean up the results. Those companies were sent in small batches to an n8n agent powered by GPT-5-mini, with a system prompt that described the author’s business and ideal customer. The agent searched the web with SerpAPI, visited company sites, and returned a size estimate, a low/medium/high fit rating, and a brief explanation before the workflow added each row to Google Sheets.
How it went
The workflow ran without manual work and turned several hours of research into a ranked list of companies to visit. It was only tested on small batches during development, so the author did not report accuracy numbers.
Tips
Keeping the batches small helped manage API spend while building the workflow. Because each company is scored on its own, the prompt should tell the agent to leave fields blank instead of guessing.

Try it yourself with n8n

Create an n8n workflow that takes exhibitors from [trade show listing URL or spreadsheet], extracts each company’s name, booth, description, and website, and then uses an AI agent to judge how closely they match my business: [describe what you sell and your ideal customer]. For each exhibitor, search the web, review the company site, assign a fit level of low, medium, or high, estimate company size if you can confirm it, and write a short reason into [Google Sheet name] as one new row per company. If a detail can’t be verified, leave it blank rather than inventing it. Pause and ask for my approval before any step that would send messages, submit forms, delete data, or make payments.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on dev.to ↗

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.