What it is
Visible Memory makes personalization inspectable. The user can see what the system knows, where it learned it, and why it used that context.
Homebase Building Block
A surface that lets the user inspect what the agent remembers, where it came from, when it was last used, and how to edit or remove it.
Memory inspector
Calls server parsing with rate limits.
| Memory | Source | Last used | Confidence | Used for | Controls |
|---|---|---|---|---|---|
| Prefers concise executive summaries | Edited by user | Yesterday | High | Writing | Edit / delete |
| Uses vendor scorecard format | Prior artifact | 8 days ago | High | Comparisons | Edit / delete |
| Avoids speculative claims | Review correction | 3 days ago | Medium | Research | Edit / delete |
| Weekly report goes to marketing lead | Calendar/email | 2 weeks ago | Medium | Reporting | Edit / delete |
Selected memory
Learned when the user edited a long research memo into a shorter recommendation format.
Learned
Explicitly saved
Examples
Used in vendor briefs and weekly updates.
Used in this answer
Memory becomes trustworthy when the user can inspect, correct, and delete it.
What it is
Visible Memory makes personalization inspectable. The user can see what the system knows, where it learned it, and why it used that context.
Problem
Persistent memory is powerful, but hidden memory creates distrust. Users need to see the system's assumptions before they can rely on it.
How it works
Why it matters
Behavior
Good behavior
I used your prior vendor-analysis format, the Q1 research export, and the tone preference you saved last week.
Bad behavior
The system silently personalizes outputs without explaining what context shaped them.
Recruiter signal
This shows product judgment around trust, AI UX, systems thinking, and the difference between useful automation and opaque automation.