Skip to content

One health record you own.

AI that can reason over it safely — instead of a dozen apps that each hold a fragment.

01 — Fragments

Health software is built around fragments.

Twelve streams of your life, held by a dozen different apps. None of them hold you.

Wearables
Wearables
Labs
Labs
Symptoms
Symptoms
Medication
Medication
Training
Training
Sleep
Sleep
Notes
Notes
Appointments
Appointments
Nutrition
Nutrition
Stress
Stress
Goals
Goals
Life context
Life context
02 — Ingestion · 03 — The object

The Longitudinal Health Profile is the durable object.

Health Core takes every event in with source and time. Provenance, continuity, uncertainty, and agency are properties of the record itself — not of any one app.

LHP

Provenance

Every data point shows its source.

Continuity

Nothing gets dropped over time.

Uncertainty

Guesses stay labelled as guesses.

Agency

Change or delete any of it.

04 — The record

What the record actually looks like.

Every entry keeps its source and confidence. Agents reason across entries instead of guessing in isolation.

Longitudinal Health ProfileYou own this
  1. Sleep below baseline

    Wearable

    Mar 12

    High

  2. New medication started

    You logged

    Mar 14

    Confirmed

  3. Resting heart rate rising

    Wearable

    Mar 18

    Medium

Illustrative sample data — not a real profile or medical advice.

Modular agents

Specialist agents should share context, not create more silos.

Health Core is designed so agents can be narrow, accountable, and useful without each maintaining a separate version of the person.

One shared Longitudinal Health Profile. Many specialist agents, each connected to the same context.

01

Domain agents

Sleep, recovery, symptom, medication, clinical prep, and experiment agents operate over the same profile.

02

Permissioned writes

Agents declare what they can read, what they can write, and which actions require explicit approval.

03

Shared context

Contradictions and low-confidence interpretations remain visible because agents do not maintain private versions of the person.

Early agent domains under exploration:

  • Sleep
  • Recovery
  • Symptoms
  • Medication
  • Experiments
  • Clinical prep

Choose how you want to start.

Use Health Core for yourself, or build agents on the shared profile.

Principles

The non-negotiables we build to.

These are engineering constraints, not slogans — the properties without which longitudinal health infrastructure cannot be trusted.

Adaptation

Recommendations are calibrated to your history — not a population average that bears no resemblance to you.

Coherence

One consistent model of the person. Agents do not contradict each other without explanation.

Continuity

Unresolved threads and follow-ups are preserved. A longitudinal agent is not a stateless chatbot.

Agency

You stay in control of your own model — more capable and informed, not more dependent on the platform.

What we will not compromise.

  • Agents stay narrow and accountable, never generic bots
  • Uncertainty is preserved, never flattened into false certainty
  • Composition is modular, so the system can be inspected and extended
  • The person owns the model, with provenance at every layer
Read the manifesto →

Agency is concrete. Over any meaningful part of your profile, you can:

  • Inspect
  • Correct
  • Approve
  • Export
  • Restrict
  • Delete
Trust, safety & agency →
Open core

Developer alignment matters in health infrastructure.

Health Core is being shaped as open-core infrastructure so the primitives can be inspected, extended, and trusted by serious builders, not hidden behind a closed wellness app.

Developer model →
Building now

Early, serious, and deliberately scoped.

QED is building the foundations first: schema, profile, permissions, provenance, and the first agent surfaces. The work is intentionally narrow before it becomes expansive.

01

Health Core schema and ingestion primitives

02

The Longitudinal Health Profile interface

03

Consent, export, correction, and provenance flows

04

Early modular agents for personal context and care preparation

Private beta

Follow or collaborate on the foundations.

We're speaking with early users, clinicians, researchers, developers, and partners who care about longitudinal context, data continuity, and safer health agents.

  • Your health model belongs to you — inspect, correct, export, or delete it.
  • Provenance and uncertainty are visible, never buried.
  • Not a diagnostic or treatment system.
Which best describes you?

Non-binding — export your data and leave the beta at any time.