See It Work · S2 Vol 1 · Sovereign Inference & Memory · Chapter 6

Doing and remembering — one foundation, seen two ways

An AI that can't remember is forgetful; a memory with no activity is a dead archive. The power is in the two fitting together cleanly — the join between them is itself recorded — which is what lets you trust the whole thing for decades, not just today.

Doing and remembering — one foundation, seen two ways — full detailed chart

The full detailed chart. Condensed for print legibility in the book; shown here at full size.

Both views sit on one foundation. A single check confirms both at once. That one shared foundation is also what lets a later volume export a self-contained, verifiable package built on this same record.
Where doing and remembering meetready

Both views trace back to the same root — proven by a single seal:

Coherence
doingreceipts pile into the record
rememberinga curated window on that record
shared foundationone seal & tamper-proofing
coverageone check covers both

One foundation, checked once — even the seam where doing and remembering meet has its own receipt.

For the technical reader — the command, and how to verify it yourself
# one line · you do not need to run this
see walkthrough
./bl-verify
# -> the one foundation both views rest on

Full step-by-step is in Appendix RX: Hands-On Demonstrations in the book.

← All walkthroughsNext: Chapter 7 →