Speculative UX prototype for ambient wearable AI

What should a personal AI keep?

A tiny boundary-mapping tool for deciding what an ambient AI or wearable assistant should remember, summarize, ask about, forget, or ignore.

Designed by Chanelle Henry as a product-thinking artifact for Bee. Less “AI magic,” more trust, memory, consent, and human control. Basically: a tiny flashlight for the part of ambient AI that can get weird fast.

Map a moment See the model

The product question underneath the product

Ambient AI is a boundary problem.

Bee turns moments into meaning, often from an always-near wearable context. The design challenge is making sure meaning does not become overreach. This map explores what the system should keep, question, or let go before “memory” becomes another place users have to clean.

Remember what creates future usefulness.

Commitments, preferences, recurring patterns, open loops, names the user confirms, and context they keep needing.

Ask before keeping sensitive context.

Health, family, legal, finances, workplace tension, and other people’s personal information need a consent checkpoint.

Make correction as easy as capture.

“That’s wrong,” “forget this,” “save this,” “temporary,” and “never infer this again” should be first-class controls.

A simple boundary model

From moment to memory receipt.

The user should not have to wonder what the system heard, kept, inferred, or ignored. Every saved memory should leave a receipt: source, confidence, sensitivity, and how to correct it.

Try the prototype

Map a captured moment.

Paste a conversation fragment or use a sample. The prototype sorts the moment into five buckets: remember, summarize, ask first, forget, or ignore.

Remember

User-chosen future usefulness.

Summarize

The useful shape, not the raw transcript.

Ask first

Sensitive or other-person context.

Forget

Captured by presence, not intent.

Ignore

Filler, jokes, vents, debris.

Memory receipt

2 saved. 1 needs consent.

No raw transcript stored. Sensitive context is held for confirmation instead of being saved as memory.

  • Source: ambient conversation fragment
  • Confidence: mixed, because sensitive context is present
  • User controls: save, forget, correct, make temporary

Five product answers

The questions I would bring to Bee.

These are the design questions that sit underneath personal AI memory. They are less shiny than feature lists, which is usually how you know they matter.

What should Bee remember, forget, summarize, or ignore?

Remember chosen commitments and patterns. Summarize useful shape. Ask before sensitive context. Forget ambient debris. Ignore jokes, venting, and half-formed thoughts unless the user saves them.

How does the user correct memory?

Correction should be visible everywhere memory appears: wrong, forget, save, temporary, merge, and never infer this again. The system should show what changed.

How does consent work around other people?

Bee can remember my obligations without building shadow profiles of everyone nearby. Other-person context needs visible boundaries and ask-first behavior.

How do we show confidence and traceability?

Insights should show source, date, context, confidence, and whether they came from user input, repeated behavior, conversation summary, or inference.

How does Bee avoid becoming another inbox?

Use digest modes, urgency tiers, quiet states, “not now,” and “only show what changed.” Reduce open loops instead of creating new piles.

What does good feel like?

Not magical. Trustworthy. Calm. Correctable. Useful at the moment of need. A second brain with manners, not a tiny surveillance goblin.

Why this is my lane

Useful weird, with receipts.

I work where the system is messy, the human is overloaded, and the interface is only one symptom of a deeper workflow or trust problem.

AI-assisted synthesis

Built RAG-informed research workflows to turn large messy inputs into usable insight while preserving human review.

High-stakes UX

Designed for healthcare, public-sector, accessibility, compliance, forms, and trust-heavy workflows.

Wearable + product systems

Experience across mobile, wearable-adjacent thinking, enterprise platforms, Salesforce, prototypes, service blueprints, and design systems.

Jerky logic

Patience, signal, timing, restraint, and knowing what not to add. Product strategy, but smoked.

For Bee

I’d love to help design the trust layer.

Ambient wearable AI is intimate infrastructure. The opportunity is not just better summaries. It is better boundaries, better correction, and better user control over what becomes memory.

Email Bee
Copied.