How I used an AI agent to recover 18 years of a .NET user group's history
I run wrocnet.org , the site of the Wrocław .NET user group. The group has been meeting since 2007, but its 18-year history was never kept in one place. I wanted a real archive: every meeting, talk, and speaker in one spot, backed by sources, and built to last. Getting there meant digging through old websites, forum posts, and archived pages, and I used an AI agent to do most of that digging.…
Wrocław .NET user group, which has been meeting since 2007, faced a challenge in maintaining a comprehensive archive of its 18-year history. The group's site had undergone three relocations, leaving gaps in the historical records. The reporter used an AI agent to assist in the research process, which helped uncover 170 meetings and 32 additional events, 185 speakers, and 300 talks.
The agent performed various tasks, including pulling archived pages from the Wayback Machine, downloading Meetup event pages, and parsing Twitter/X profile data. It verified each source carefully, marking estimated dates and explicitly labeling them as estimated when further confirmation was required. The workflow included assigning repetitive research tasks to the agent, verifying findings, and merging the results into Jekyll posts.
The repository's initial list of old meetings provided a basis for the research, but numerous gaps were identified during the process.
The reporter followed strict rules to ensure the research remained useful and trustworthy. These rules included verifying announcements, after-event reports, meeting numbers, and conflicting sources before drawing conclusions. Collaborators Tymoteusz Wojnarowski and GitHub's Copilot code review system also contributed to the project by uncovering additional historical data and reviewing the pull requests.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
