---
title: "Conference attendee research briefing"
canonical: "https://agenticfeats.com/c/conference-attendee-research-briefing-claude-code/"
agents: ["Claude Code"]
evidence_grade: "B"
outcome: "completed"
job_type: "Research"
roles: ["Founder or owner", "Sales"]
source_url: "https://technicallycurious.substack.com/p/have-claude-browse-the-web-for-you"
source_date: "2026-03-16"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Conference attendee research briefing

Claude Code researched 40 conference attendees in parallel through Chrome MCP, using the author's LinkedIn login, and compiled everything into one briefing.

Result: A full participant briefing on 40 people was ready for review within 5 minutes, replacing an evening of manual LinkedIn clicking.

## How it was set up

Claude Code with the Chrome MCP connector, logged into LinkedIn in the separate browser profile Claude controls. Exa and Firecrawl are used for wider research and scraping.

## Worth knowing

Prompt injection is a risk while browsing. The authors advise a separate browser profile and no logins to banking or email.

## Prompt

```text
Use your Chrome MCP to research each of these conference attendees on LinkedIn in parallel: [list of names]. For each person, summarise role, company, background, and conversation hooks. Compile one briefing document for me to review.
```

## Evidence note

Author states 40 people and 5 minutes; no output shown

## Sources

- Original: https://technicallycurious.substack.com/p/have-claude-browse-the-web-for-you

## The receipt

- Agent: Claude Code
- Evidence: Numbers (grade B, a specific number stated)
- Outcome: Completed
- Job type: Research
- Roles: Founder or owner, Sales
- Source: Blog
- Published: 2026-03-16
- Added: 2026-10-13