Guides · intermediate · Reading path · 5 parts

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.

Route map connecting the five parts of the AI work memory guide to one plain-text hub: connected work context, email and calendar capture, local meeting transcription, script-first processing, and daily commands

The numbers match the guide order, but this is a map rather than a dependency chain. Start with the overview for the whole system, follow the route, or open the capture, transcription, processing, or daily-command part on its own.

5 parts 40 min est. Published jul 23, 2026

Start Guide → ← All Guides

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.
15 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.
13 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
Claude Code skills: building a workflow that runs itself The control layer of my work system is markdown and small scripts. How a workflow combines Claude Code skills, rules, model routing, and parallel sub-agents.
6 min