> For the complete documentation index, see [llms.txt](https://docs.bitpers.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bitpers.com/feature-modules/face-hunt.md).

# Face Hunt

Smart, Consent‑First Discoverability

### TL;DR

**Face Hunt** is a privacy‑first people search for your media. Opt‑in discoverability helps users instantly surface photos of specific people across events, memory boards, and murals.

***

### 1) What is Face Hunt?

A selective, consent‑driven face search that lets users filter content by participants. Great for events, shared boards, and public creators who choose discoverability.

**Why it matters:** Finding yourself (or friends) across thousands of photos is painful. Face Hunt makes it instant—without compromising consent.

***

### 2) Value Proposition

* **Consent by design:** Opt‑in controls at user and board levels.
* **Fast recall:** Filter feeds by people; “photos of me.”
* **Event superpower:** Attendees instantly find all photos they appear in.
* **Creator mode:** Public figures can enable large‑scale discoverability.

***

### 3) Core Features (v1 & v1.1)

* **Opt‑in enrolment & visibility controls.**
* **People filters** in feeds and boards.
* **Per‑mural/board toggles** and safe defaults.
* **Local processing preference** where feasible; minimal cloud data.

**Polish (v1.1)**

* Better disambiguation and liveness checks.
* Shareable “photos of me” views (within access limits).

***

### 4) Use Cases

* **Events:** Find yourself and friends post‑concert or wedding.
* **Memory Boards:** Sort trip photos by who’s in them.
* **Public Murals:** Opt‑in creator discoverability.

***

### 5) Roadmap (Illustrative)

* **Q1:** Opt‑in flow; per‑space toggles; people filters.
* **Q2:** Liveness & impersonation defenses; improved matching.
* **Q3:** Creator verification; controlled public discoverability.

***

### 6) Metrics

* Opt‑in rate; searches per user; success taps after filter.
* False positive/negative rate (internal); report/appeal rate.

***

### 7) Risks & Mitigations

* **Privacy sensitivity:** Explicit consent, clear UI, per‑space control, easy opt‑out.
* **Misidentification:** Conservative thresholds; user confirmations; reporting.
* **Abuse:** Rate limits, verification for public discoverability.

***

### 8) Integrations

* **Events:** On‑site discovery and recap.
* **Memory Boards:** Fast person filters.
* **Murals:** Personalised feed slices (“find me in this mural”).
