I need an AI-driven agent that will log in to my LinkedIn account, pull my entire first-degree network, then let me filter, sort, and ultimately remove connections by the two factors that matter most to me: Job title and Location. Here is what success looks like for me. The agent retrieves every connection, reads whatever public data LinkedIn provides (job-title string, current company, city / country, etc.), and shows me a preview table where I can type or paste the title and location rules I care about. With one confirmation click, the tool should disconnect any profiles that do not match those rules. I want a summary CSV at the end listing who stayed, who went, and why, so I can keep the audit trail. I am comfortable running Python, so a clean script or lightweight Flask/Streamlit front end would be ideal, but I’m open to other languages if you explain the setup clearly. Please avoid anything that could violate LinkedIn’s terms of service; official API, Selenium, or similar approaches are fine as long as they work reliably. Deliverables: • Fully working code with clear authentication steps • Simple interface to set job-title and location filters, preview results, and approve removals • CSV or JSON report of all actions taken • Quick start guide so I can rerun the process myself Acceptance criteria: when I test on a subset of 1000+ connections, the agent correctly identifies at least 95 % of matches to my criteria and completes the disconnect process without manual intervention other than the single approval click.