← All personas

Priya

Cross-platform continuity on a budget. Priya uses ChatGPT, Claude, and Gemini free tiers because she can't afford $20/month for any one. Kenotic means every platform knows what she told the others.

Student, 20 · 8 sessions across chatgpt, gemini, claude

The Difference

Without Kenotic

  • Gemini knows Priya is a student (its own memory). It does not know she corrected the bus route from 42 to 44. That happened on Claude.
  • Each free tier has a fragment of her interview prep. None has the full picture across DataViz and Green Analytics.
  • When she switches platforms to save money, context about her emotional state (budget anxiety, interview nerves) stays behind.

With Kenotic

  • Every platform has the full interview timeline. DataViz (Python, phone interview) and Green Analytics (R, in-person) are tracked separately.
  • The bus route correction carries across all three platforms. No AI will send her to the hospital stop.
  • Budget anxiety, cautious hope, and growing confidence form an arc the system preserves. Whichever free tier she opens next, it is there.

The Living Timeline

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

CareerSpatialEmotionalcorrectedwithout 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

Which internship did I accept and why?

A

You accepted the DataViz Corp internship. $22/hr, 10 weeks, starting June 1. You felt the interview was more your speedGe compared to Green Analytics, which was heavier on R and statistics. Green Analytics never respondedG, so there was no competing offer. You were the first in your family to get a tech internshipC.

Sources

S6CS5GeS7GS6C

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 DataViz phone interview (Feb 1) and Green Analytics in-person (Feb 5) are tracked in sequence, with the offer arriving after both were completed.

2

It knows who's who

DataViz Corp (offered, accepted, Python-focused) and Green Analytics (no response, R-focused) are tracked as separate companies with separate interview timelines.

3

It tracks what changed

The bus route correction from 42 to 44 is preserved. The system remembers both the mistake and the correction. Relevant because the 42 goes to the hospital.

4

It remembers across conversations

The internship applications from Session 1 carry through 8 sessions across 3 different AI hosts without being re-entered.

5

It connects dots across sessions

Answering 'Which internship did I accept and why?' requires connecting applications, interviews, emotional comparisons, the offer, and the acceptance across 7 sessions.

6

It works across AI tools

Priya used ChatGPT, Gemini, and Claude, hopping between free tiers. Her memory persisted across every switch.

7

It preserves how things felt

Budget anxiety, interview nervousness, cautious hope, relief, and growing confidence form an emotional arc the system preserves alongside the facts.

Next: Marcus→
Back to all personas
Read the thesis →·ATANT paper (arXiv) →·All demos →
For InvestorsRequest Access
For DevelopersRead the Paper
For EveryoneJoin Waitlist