Memory & continuity

Practice area card · One-pager · Version 1.0 · August 2026

Download as PDF

Free. No email required.

What agents read, and what survives the session.

Foundation area. This is one of four practice areas the field guide treats as running underneath all three shifts: today it's the only one of the four that's live.

  • The term “Career Delta File” comes from Manager Tools, not from me. I've kept one for about a decade — a plain running log, month headings, bullets in reverse chronological order, everything that doesn't fit on a resume but ends up building one: the presentations, the workshops, the things I learned, the things I got wrong.
  • The discipline is simple: write down what changed, on a cadence, before you have to trust memory to hold it. A few minutes and a place to write is enough to start. No system required.
  • Here's the bridge to agent memory, and the reason this is the card's whole point: an agent that finishes a session and forgets everything has the identical failure mode as a person who stopped updating their file. Real work happened. None of it got written down.
  • Being honest about the gaps is part of the practice. It's not something I hide. My own file has stretches where I stopped updating — I leave them visibly blank. I don't backfill a falsely clean record.
  • I'm running one live experiment on top of this: using AI to parse a decade of entries and help backfill what's missing. It's tooling around the practice. It doesn't replace it, and I don't yet know if it's something I can share.

What's Behind This Card

A decade of gaps cost me more than I expected, and that full story is at The Career Delta File: A Decade of Notes I Almost Lost.

This is one of six cards today. The field guide maps seventeen practice areas, and I'm growing this set as each one earns its own depth.

This is a fit question, not a recipe. Where your team actually sits against this list, and what that's costing, is what the Engineering Ways of Working Diagnostic is built to find.

Part of the AI-Native Ways of Working field guide