← All personas

Dr. Amara

Clinical accuracy across devices. A diagnosis changes from Type 2 to LADA. The system tracks the correction and never reverts, even when switching from desktop to mobile.

Doctor, 42 · 8 sessions across claude, chatgpt, gemini

The Difference

Without Kenotic

  • Gemini knows Dr. Amara is a physician (its own memory). It does not know Sarah Lin's diagnosis was reclassified from Type 2 to LADA. That happened across Claude and ChatGPT sessions.
  • Two Sarahs: Sarah Lin (patient) and Sarah Mitchell (nurse). Could be confused if the system only has a name and no temporal context.
  • The old diagnosis (Type 2) might persist in one platform's memory while the corrected diagnosis (LADA) exists in another.

With Kenotic

  • The reclassification from Type 2 to LADA is tracked as a correction with timestamps. Every platform sees the current diagnosis.
  • Sarah Lin (patient, LADA) and Sarah Mitchell (charge nurse, night shifts) are structurally disambiguated. No confusion possible.
  • The full clinical arc (initial labs, reclassification, treatment change, stable control) is accessible from any device Dr. Amara uses.

The Living Timeline

Scroll through to see how facts, corrections, and context build over time.

HealthCareerRelationshipsEmotionalcorrectedwithout continuitywithout continuitywithout continuitywithout continuity

Reconstruction

Ask a question that requires connecting facts across sessions, hosts, and time. See where each part of the answer comes from.

Q

What happened with Sarah Lin's diagnosis?

A

Sarah Lin was initially diagnosed with Type 2 diabetesC in January, but follow-up labs in February revealed GAD antibodies, leading to reclassification as LADAG. Her treatment changed from metformin to basal-bolus insulinG, and she is now in stable glycemic controlC.

Sources

S1CS3GS4GS8C

How It Works

Four steps. No cloud. No LLM at read time. Retrieval is deterministic, so answers don't change when you switch models or when the provider ships an update.

Step 1

Ingest

You talk to any AI. The bridge captures structured understanding: facts, corrections, temporal order, emotional context.

Step 2

Store

Facts, corrections, temporal order written to a local SQLite file. On your device. No cloud.

Step 3

Reconstruct

You switch platforms. The bridge traverses the graph across all sessions, hosts, and time periods.

Step 4

Deliver

Grounded answer from specific moments. Every claim traced to a source session. No hallucination.

7 Points of Continuity

Each point represents a capability that requires genuine continuity, not retrieval alone.

1

It knows what happened when

The LADA reclassification in February is tracked as occurring AFTER the initial Type 2 diagnosis in January. The system preserves the diagnostic timeline.

2

It knows who's who

Sarah Lin (patient, LADA) and Sarah Mitchell (charge nurse, night shifts) are tracked as separate people. Critical in a clinical context where confusion could be dangerous.

3

It tracks what changed

The Type 2 to LADA reclassification is preserved as a correction, not a replacement. Both the original diagnosis and the correction are visible with temporal context.

4

It remembers across conversations

Sarah Lin's initial labs from Session 1 remain available through Session 8 without re-entry. The clinical history accumulates.

5

It connects dots across sessions

Answering 'What happened with Sarah Lin?' requires connecting the initial diagnosis, the reclassification, the treatment change, and the current status across 8 sessions.

6

It works across AI tools

Dr. Amara used Claude, ChatGPT, and Gemini across her sessions. The LADA reclassification happened on ChatGPT but is fully available when she returns to Claude.

7

It preserves how things felt

The weight of reclassifying a diagnosis (Session 3) and the relief when the patient responds well (Session 6) are preserved as part of the clinical narrative.