Anthropic engineer reveals how Claude transforms email into structured databases

The Gist

• Felix Rieseberg used Claude to parse years of email receipts into a 3D floor planner
• The biggest barrier to AI adoption is psychological, not technical
• Claude can automate any repetitive task if users develop the muscle memory to ask

• The biggest barrier to AI adoption is people not realizing they can ask AI to solve almost any problem.
• Your email is an untapped gold mine of personal data that can be structured into databases using Claude.
• Live artifacts are Claude’s answer to keeping your personal dashboards always up-to-date with real-time data from connected services.
• Kids are the best AI users because they aren’t afraid to ask for things, unlike adults who have learned what computers can’t do.
• When Claude makes mistakes, debug your workflow, not the model, by treating it like a collaborator who needs better instructions.
• Gemini 3.5 Flash rivals leading frontier coding models in Google’s benchmarks while running four times faster.

• Use Claude to parse and structure personal data from emails into actionable databases (e.g., inventory management).
• Build live, auto-updating dashboards by connecting Claude to real-time data sources like Spotify, Gmail, and Notion.
• Choose Opus over Sonnet when you need Claude to interpret ambiguous or high-level requests, not just execute well-scoped tasks.
• Test Google’s new AI tools (e.g., Gemini 3.5 Flash, Omni) for speed and multimodal capabilities but be wary of unfinished features.

• 4 times faster (Gemini 3.5 Flash runs four times faster than leading frontier coding models.)
• 10-second videos (Omni creates 10-second videos, compared to Sora’s 6 or 7 seconds.)