We were doing research wrong.😱 Every Monday morning, 4 of us would independently search ArXiv, Google Scholar, and Semantic Scholar for papers on AI automation and document processing. 3 hours each. 12 hours total team time. Then we'd compare notes and realize we'd all found the same 7-8 papers. Complete duplication of effort. THE BREAKING POINT: One Monday, our lead researcher was sick. We had a client call Tuesday needing current research on AI extraction methods. Nobody had done the Monday search. We looked unprepared. "We can't keep doing research this way. There has to be a better system." WHAT I BUILT: n8n workflow that runs daily at 8 AM: SCHEDULE TRIGGER - Fires every morning before team arrives ACADEMIC SEARCH NODE - Searches ArXiv, Google Scholar, Semantic Scholar simultaneously for "AI automation document processing" papers PROCESS RESULTS - Extracts paper data from API responses VALIDATION FILTER - Ensures paper has abstract (>50 words), PDF link, and author information (removes incomplete entries) LIMIT TO TOP 5 - Selects most relevant papers only GOOGLE SHEETS INTEGRATION - Logs to spreadsheet with: Title, Authors, Abstract, PDF link, Citation count, Source, Year, Date added SLACK NOTIFICATION - Sends formatted morning digest to #research channel The whole workflow took 30 minutes to set up. THE RESULTS: Team arrives each morning to curated research digest. Zero manual search time. Everyone sees same papers. Complete metadata automatically captured in spreadsheet. From 12 hours weekly search → 45 minutes weekly review. Found 3 papers in last 4 months that directly influenced client projects. Would've missed them with old manual approach because they were published Thursday afternoon (we only searched Mondays). CURRENT STATUS: Been running 4 months. Zero maintenance required. Google Sheet now has 480+ papers with full metadata. Searchable knowledge base that grows automatically. Easy to export to CSV or analyze. Team actually reads MORE papers now. Discovery friction removed.

There's something special about learning by doing, especially when you're building across time zones with great people. This Sunday at 10:00 AM CET, I teamed up with my business friend Rudolf Van Loggerenberg from New Zealand for another Sunday build session. While most people were enjoying their Sunday morning coffee, we were deep into voice AI development. What we built: + An outbound voice call agent – capable of making autonomous phone calls + A website embedded voice agent – implemented as a widget for realtime visitor interaction Our tech stack: - ElevenLabs – for natural voice synthesis & agent infrastructure - n8n – workflow automation & AI orchestration - Antigravity – browser control - Lovable – rapid frontend development - Hostinger – hosting & deployment Weekend sessions like these are where the real learning happens. No pressure, just curiosity and collaboration, building something from zero to functional in a few hours. Interested in joining a future session or want to learn more about voice AI agents? Drop a comment or send me a message always happy to connect with fellow builders or enthusiasts!