Business and Sales · Blog · 🌐 International · via agentusecases.ai
An n8n agent researches trade show exhibitors and scores each one as a potential client
A consultant built a workflow that scrapes the exhibitor list, researches each company online and writes size, score and reasoning to a Google Sheet.
- Profession
- Salesperson, Entrepreneur
- Tools
- n8n, Bright Data, GPT-5 mini, SerpAPI, Google Sheets
- Source
- dev.to ↗
- Country
- 🌐 International
- Found via
- Agent Use Cases ↗
- Report date
- August 29, 2025
- Verified on
- November 2, 2026
See more: AI for salespeople · AI for entrepreneurs
What they did
Andre Moreira of lyfX.ai built Tradeshow Scanner in n8n. Bright Data fetches the exhibitor list from the show's website, code extracts name, description, booth and website, and companies go in batches to an agent running GPT-5 mini. The agent's prompt describes his company and ideal client; it searches with SerpAPI, reads each company's site and returns size, a low, medium or high score and the reason, which go into a spreadsheet.
How it went
The author says the workflow turns hours of research into a prioritized list of booths to visit and companies to follow up with. He only ran small batches during development to keep API costs down and did not publish any accuracy measure for the scores.
Good to know
Each company is judged independently, and it helps to tell the agent to leave fields blank rather than guess. The sanitized workflow is published as a gist for anyone who wants to adapt it.
The prompt
I'm visiting the [name] trade show and have the exhibitor list [paste or link]. My company sells [what we sell] to [ideal client]. For each exhibitor, research their website, estimate company size, give a fit score (low, medium or high) with a one sentence reason and return a table sorted from highest to lowest. If you can't find the information, leave the field blank instead of guessing. Don't contact any company.
Replace what is in [brackets]. Prompt written by us from the account, not a literal copy of the source. Do not paste other people’s personal data (privacy laws such as LGPD and GDPR apply).
Summary in our own words. Results as stated in the original account; we have not tested or audited them. Read the source ↗ Case found via Agent Use Cases; text and prompt rewritten by us. Found a mistake?
Similar cases
01A neighborhood auto shop reminds customers about quotes without becoming spam
An auto repair shop in Curitiba set up automatic WhatsApp quote follow-ups using AI.
02Pre-qualify leads before they reach a salesperson
Futurepedia built an agent that researches each company, writes a fit summary and forwards the best leads.
03Separating business expenses from personal card statements
The author had Claude talk through the first few statements to learn her patterns before classifying the rest.
04An automatic 6 a.m. briefing on who you're about to meet
A Zapier agent reads your calendar, researches external attendees and sends the summary to Slack.
05Automatic preparation for sales meetings
Annika Helendi used a template that triggers on events with "discovery" in the title and researches the contact.
06Researching 50 target companies and filling in the CRM
A Dutch consultant filters the list by hand, then the agent researches each company and creates records ready for outreach.
07Giving an agent a server and the mission of building a business
A dev let Claude Code run every 30 minutes on a VPS, with memory kept in files, asking for help via Telegram.
08Discovering the problem wasn't the model, it was the question asked to customers
An entrepreneur improved a demand forecasting model, but only made progress in sales after changing the question asked to customers.