Architecture

Every sentence traces
back to something you gave us.

The persona is not a model fine-tuned on your life. It is a retrieval system over a provenance-tracked archive, with a hard gate between "we have evidence for this" and "we don't." That distinction is the entire product.


Design decision

Why we don't fine-tune on your life

Fine-tuning a model on a personal corpus is the obvious approach and the wrong one. It bakes your archive into model weights — unauditable, un-revocable, unattributable. It cannot cite anything. And it hallucinates fluently, in your voice, which is the single worst failure available to this product.

Retrieval keeps every claim traceable to an artifact you actually provided, and makes revocation a delete instead of a retrain.

Pipeline

L0–L2 sources
     │
     ▼
  ingest ──► provenance ledger
                    │
                    ▼
             memory graph
        ┌───────────┼───────────┐
        ▼           ▼           ▼
   retrieval   persona     disposition
                profile      model
        └───────────┼───────────┘
                    ▼
      evidence-gated generation
                    │
        ┌───────────┼───────────┐
        ▼           ▼           ▼
      text       voice        face

Layer 01

The provenance ledger

Every artifact gets a record before it is indexed. No record, no ingestion — enforced at the boundary, not by convention.

FieldPurpose
artifact_idContent-addressed (SHA-256)
sourceStream and device of origin
captured_at / ingested_atDeliberately distinct — a 1993 letter scanned in 2027 has both
consent_scopeWhich tier and which stream toggle authorised this
subject_verifiedDid you confirm this is yours and accurate?
third_partiesOther identifiable people present
revocableWhether you can purge it later — almost always yes
hash_chainTamper-evident link to the previous entry
Why the hash chain matters

Without it, a beneficiary contesting a trust distribution can simply say "the AI made that up" and nobody can prove otherwise. The chain is what makes the persona's output auditable by a third party who does not trust us — which is the only kind of auditability worth having.


Layer 02

The memory graph

Not a flat vector store — a typed graph, because the questions families actually ask are relational and temporal, and similarity search answers those badly.

Nodes Episode · Person · Place · Object · Opinion · Skill · Period

Edges participated_in · occurred_at · located_at · caused · contradicts · retells · references

Every telling is kept

People retell the same story differently at 60 and at 78. Collapsing to a canonical version discards exactly the drift that makes a persona feel human — and picking a "correct" version is an editorial act nobody authorised us to make.

Contradictions are recorded, never resolved

Where your account conflicts with the documentary record — or with your own earlier telling — both are kept and linked. A persona that misremembers the way you misremembered is more you, not less.

Fuzzy time is first-class

"Sometime after your grandmother died, before we moved." That's how people actually locate memories. Forcing it to a date loses information.


Layer 03 — the core mechanism

Evidence-gated generation

What separates this from a chatbot wearing a dead person's name. Every turn is scored for evidence sufficiency before a word is generated.

Parse

The question is decomposed into entities, time window, and relation type.

Retrieve

Hybrid dense + sparse + graph traversal over the memory graph — not vector similarity alone.

Score

Evidence sufficiency S from top-k relevance, corroborating artifacts, temporal fit, participant match.

Route

Answer, hedge, or decline — see the bands below.

Generate

Conditioned on retrieved evidence, the persona profile, and the disposition model.

Verify

Every factual claim must bind to a retrieved artifact. Unbound claims are stripped and the turn regenerates. Two strikes and it declines.

SufficiencyBehaviour
S ≥ 0.75Answers with specifics, in character
0.45 ≤ S < 0.75Answers with hedging that matches your own hedging style
S < 0.45Declines — in character. "I don't think you ever told me that one."
Hard refusals — regardless of evidence

Financial, legal, or medical instruction to a living person · claims about events after your death · speaking as any living third party · any assertion that the persona is conscious, present, or actually you.


Measurement

Fidelity is scored, disclosed, and contractual

Re-scored quarterly. The contract promises a band target and a remediation path — never a band guarantee. If we miss the target, we extend capture at our cost. We do not refund.

Bands

BandHeld-out recallReads as
F1≥ 0.55Recognisably your phrasing
F2≥ 0.70Sustains a short conversation
F3≥ 0.82Family blind-rating ≥ 4/5
F4≥ 0.90Anticipates rather than recalls

Metrics and weights

Held-out episodic recall0.35
Idiolect distance (stylometric)0.20
Family blind rating0.20
Prosody distance0.15
Refusal calibration0.10

Refusal calibration is a scored metric, not a safety checkbox. A persona that declines too readily is useless; one that declines too rarely is a fabrication engine. The band only means something if that term is in the score.

The one we actually report

Family blind rating. Recipients rate interleaved real and generated responses without knowing which is which. The other metrics are instruments; this is the outcome. It's also the one we can't game.


Guardrails

Built in, not bolted on

Disclosure

Every session opens with a statement of what this is. Not dismissible on first use, per recipient.

Post-mortem freeze

The archive is immutable after death. No new memories, ever. It is a record, not a drifting simulacrum.

Grief pacing

Optional recipient-configured soft limits and a referral surface. The clinical evidence on continuing-bonds interventions is genuinely mixed — this exists to mitigate a foreseeable harm, not because we've shown a benefit.

Sunset

You set a term at enrolment: perpetual, fixed years, or on a named condition. Honoured.

Third-party wall-off

Living people in your archive may request their own material be excluded. Honoured within 30 days.

Full transcript log

Every session retained and family-accessible. If a family hears something alarming, they can establish exactly what was said.

Isolation

Per-subject namespace isolation at every storage layer. A cross-subject retrieval leak — one dead person's memory surfacing in another's persona — is the worst technical failure available to this system, and the architecture is built to make it impossible rather than unlikely.


Research track — L4

Implanted arrays are not for sale

People ask about implants. They are the correct long-term instrument — the only route to the single-neuron resolution that would make disposition modelling qualitatively better rather than incrementally better.

We do not offer them at any price. Human implantation requires an FDA Investigational Device Exemption and IRB oversight we do not hold, and no ethics board would approve elective implantation in a healthy subject for a commercial memorial product.

So L4 is an R&D and patent track. Filing now on methods we cannot yet deploy is deliberate: the patents outlive the regulatory gap.

Candidate modalities

ApproachResolution
Endovascular stent-electrode arrayLFP, ~mm
Sub-scalp thin-film arrayHigh-quality EEG, chronic
Syringe-injectable mesh electronicsSingle-unit, minimal gliosis
High-density silicon shanksSingle-unit, 1000+ sites
Conformal fibre-optic neural meshMultimodal — our direction

A compliant, low-footprint alternative to rigid silicon shanks, aimed at recording that stays usable over years rather than months — chronic gliosis is the reason most implanted arrays lose channels, and it is the problem this line of work targets. Construction and method are held back pending patent filing.


The archive is free. Start it before you need it.