Build an AI Work Memory

Your email, meetings, and documents wired into one plain-text folder an AI can actually read. The full build, from getting data out of a mailbox with no API access, to transcribing meetings without uploading the audio anywhere, to the handful of commands that run the whole thing each morning. Start with the overview, then take the pieces in order. Each one stands on its own if you only want that part.

Parts

Est. Time

39 min

Published

jul 22, 2026

Chapters

01
My AI Was Smart. It Just Couldn't See My Job. My work context was scattered across email, meetings, documents, and notes. So I wired it into a private Obsidian vault Claude Code can read.
16 min
02
Capturing Email and Calendar Without a Mailbox API Microsoft Graph and IMAP were off the table, so I used Power Automate, OneDrive sync, and one 15-minute scheduled task to pull email and calendar into a local inbox.
11 min
03
Transcribing Meetings Locally Turning meeting audio into text on your own machine, so the recordings never leave it.
Coming Soon
04
Most of My AI Pipeline Isn't AI By volume, most of my AI pipeline is plain Python. The model is a small, expensive part I call as little as possible. The script-first split, and why it wins.
6 min
05
One Command a Day: The Skills That Run the Vault The whole control layer of my work system is a folder of markdown files. How a real workflow is built from Claude Code skills, rules, and parallel sub-agents.
6 min

Start Guide →