Under the hood

How EloDtx Works

Three systems. One purpose. Building real human connection at scale — with whispers, proximity, and a model that never stops learning.

The Whisper System

EloDtx never writes messages for users. It whispers suggestions.

The Philosophy

Human connection is irreplaceable. EloDtx's role is not to speak for you — it's to give you the clarity to speak better yourself. Every suggestion is framed as an observation, never a script. You decide what to do with it.

Example whisper

"She mentioned not going back to her hometown much — her answers suggest this means something to her. This could be worth exploring gently."

Ephemeral Processing

Message content is never stored. EloDtx reads a conversation context window in real time, extracts behavioral patterns, and immediately discards the raw text. Only the patterns remain — anonymised, aggregated, and tied to behavioral dimensions rather than anything you actually said.

I haven't been back to my hometown in years honestly…

That's interesting — what keeps you away?

Whisper

She mentioned not going back to her hometown much — her answers suggest this means something to her. This could be worth exploring gently.

Visible only to youBased on weeks of behavioral dataCombined with live conversation signals

The Proximity Flow

From opt-in to conversation — every step privacy-first and consent-gated.

1

User enables proximity

With a single tap the user opts in. Proximity is always off by default — active consent is required every session.

2

Geohash location sent (±500m, never exact)

The device encodes the user's position into a geohash — a ~500m × 500m area code. Exact coordinates never leave the device.

3

EloDtx runs compatibility check (<2 seconds)

The engine cross-references all nearby opted-in users against the requesting user's 138-dimension behavioral profile in real time.

4

Apple Watch haptic tap

If a high-compatibility match is within range, a discreet haptic pulse fires on the wrist. No sound. No visible notification.

5

5-element alert card appears

The watch face shows compatibility score, shared traits, current activity, distance, and two action buttons.

9:41
Nearby Match84%
Creative pursuits
Deep conversations
Morning person
Having coffee
~150m away
6

Profile request sent

Tapping 'Connect' sends an anonymous interest signal. The other person receives an identical alert and chooses independently.

7

Consent → Messenger unlocks

Only when both parties tap 'Connect' does the messenger open. No one-sided reveals. No pressure.

The Behavior Learning Loop

Every interaction — active or passive — refines the model. The profile is never static.

Passive Signals

Scroll behavior
Session timing
Notification response
🧠Dynamic
Profile
138 dimensions
Real-time updates

Active Signals

Intents sent
Messages exchanged
Event attendance
Know Me answers

All behavioral signals are processed ephemerally. Message content is never stored — only anonymised patterns are retained to improve the model.

The Training Path

We're building our own model — one that has never existed before, trained exclusively on connection data.

NowCurrent

Claude API Layer

EloDtx runs on Anthropic's Claude API with proprietary prompting, fine-tuned for connection intelligence. This gives us production-grade AI while we build our own.

Month 12–18

Qwen 3.5 Fine-Tuning

Fine-tuning Qwen 3.5 on our proprietary behavioral dataset — 508 real user profiles, conversation patterns, and outcome data from the Baeyond POC.

Month 18–24

Hybrid Deployment

Running our fine-tuned model alongside Claude for validation. Gradual traffic migration as our model proves equal or superior performance.

Month 24+

Full Proprietary EloDtx Model

Complete independence. A model trained exclusively on connection data, optimized with TurboQuant compression for 4.9x efficiency.