Org Structure & Email Scraping Agent

I want a self-contained software agent that, when I feed it the name or domain of a medium-sized enterprise, automatically pieces together the company’s full organisational chart and returns a verified corporate email and number for every person it finds. The agent may explore open data reservoirs—our internal databases, public directories and employee social profiles—but it should not rely on any authenticated endpoints, API keys or user log-ins.

You are free to choose the language and stack, though Python plus libraries such as Scrapy, Beautiful Soup, Selenium or similar web-automation tools would make sense. The final output needs to be delivered in both machine-readable (JSON or CSV) and human-friendly form: a hierarchical tree or graph that clearly shows reporting lines, departments and titles.

Deliverables
• Source code with clear comments
• A runnable script or container image
• Sample run demonstrating a full org chart and matching emails for one test company
• Brief README describing setup, usage and any limits or fallbacks

Acceptance criteria
1. Completeness: the returned hierarchy aligns with publicly available information for the test company.
2. Accuracy: at least 90 % of captured emails pass validation (RFC syntax and MX check).
3. Zero credential dependency: the agent runs end-to-end without manual log-ins or tokens.

Once the proof of concept is accepted, I may commission further work to refine accuracy, add multi-company batching and integrate visual reporting.