Zenlo isn't one app — it's a single clinical engine decomposed into atomic, reusable blocks across seven families. Each product is an assembly of the same blocks. This is the whole system, with an honest status on every part.
Eight steps, from an uploaded file to a structured clinical reading. Tap a step to see what happens inside it.
One block, many products. The Clinical Engine (B1–B6) is reused across seven product configurations — the same parsing, the same patterns, the same biological-age and insulin-resistance math. Build a capability once; ship it everywhere. That reuse is the leverage behind a one-engineer company.
Every atomic capability, its current status, and the AI model behind it where one is used. Filter by maturity — we label what's live and what's still on the bench.
Unified Postgres + Auth + RLS + Storage + consent + data export/delete.
One user gets revocable read / limited-write access to another's data.
Restricts who can create accounts on a given instance.
Reference catalogue of 102 biomarkers: code, name, unit, reference range by age/sex, category.
PDF / photo / text / manual entry becomes structured biomarker JSON. This is the OCR + extraction step.
15 validated patterns plus interaction analysis across 8 relationship types between them.
Insulin-resistance index from fasting glucose × insulin, with a clinical threshold.
Weighted Z-score model across 8 biomarker categories vs age/sex reference ranges.
Longitudinal tracking with directional meaning (lower / higher / U-shape is better).
The same dataset through five models with F1 comparison — the basis for our benchmark and preprints.
A 4-tab experience (Stories / Numbers / Ask / You) — "Duolingo for your body".
Full recovery shell: Today / Treatment / Meds / Labs / Team / Journal / Ask / Docs.
Educational story templates that explain a result, with a safety post-filter.
4-layer memory: standing history + live context + retrieval + tools (trends, adherence, documents, schedule).
Multi-type medical documents: labs, imaging, consults, prescriptions, discharge.
Supplement / prescription banks + schedule + intake log + % adherence.
Daily mood/fatigue/sleep ratings + chip symptoms + an NIH-validated assessment.
Doctor cards with specialty, facility, schedule, primary flag, caregiver block.
Upcoming cycles, visits, labs, and pre-visit prep materials.
A ladder-of-trust funnel that collects profile data in tiers, with inline follow-ups.
Apple Health / Oura / Whoop / Google Fit / Garmin / Fitbit connectors + a daily insight.
Side-by-side "you see / employer sees" + a HIPAA / BAA / ZDR / RLS technical fold-out.
Alternate rendering: raw numbers, 6-month delta, reference-position bar, model info.
Company → admins → roster → communications → launch → day-0 countdown.
Metric cards + monthly insight + cost-avoided YTD + attention items.
5-stage adoption funnel + completion + department breakdown (engagement only).
Population pattern trends + benchmark vs norm. Per-department health is never shown, regardless of size.
Modeled estimate with confidence interval, value categories, and a claim / don't-claim matrix.
Executive view + QoQ curve + compliance grid + multi-length PDF export.
Status / department / invited / last-signed-in only. Cannot surface activity by design.
Funnel metrics + recommended nudge + tone presets + automation timeline.
Seat usage + next invoice + payment method + billing history + ACH/PO.
Compliance status cards + data-flow diagram + subprocessor table + downloadable docs.
k ≥ 10 enforced server-side on every aggregate query, with visible suppression. Raisable, never lowerable.
2,534 documents in a vector store (1,349-doc bootstrap core) spanning population data and literature, 2000–2025.
Weekly PubMed saturation scan → a gap map by topic × year → top-3 topics.
7 hypothesis types per topic (confirmatory, contradictory, null, mediator-shift, subgroup-reversal, threshold-break, interaction-only), scored to top-3.
Parallel testing: logistic regression (OR + 95% CI), interactions, stratified, threshold, propensity matching, survey weights.
Structured report: winning hypothesis, finding, product implication, confidence, rejected hypotheses, next step.
5-model parallel review — structure, citations, novelty, adversarial critique, and a healthcare-tier clinical-validity model.
Journal-aware drafts with real citations pulled from the literature stage.
Post-processing dedup + a universal study-design validator across any topic.
Safety layer: the agent reads broadly but writes only to a whitelisted workspace — no new pages, no deletions.
Command intake from dev / research / pm / marketing channels → the right agent group.
Planner → Generator → Evaluator with sprint contracts and automated browser testing.
6 lifecycle events — permission checks, auto-format, state-save before compaction.
Timestamped branches + auto-commit + auto-push → preview deploy → human review.
Employer sourcing + LinkedIn + email + dialer + CRM pipeline.
A ready pilot contract structure with a stop/go ROI gate.
A tiered per-member-per-month pricing model from pilot to enterprise.
A structure for engaging practising MDs as clinical advisors.
AI + healthcare-data consulting as parallel income during the build phase.
A claim / don't-claim matrix + a subprocessor registry + change-notification policy.
A forbidden-word filter + tone registers per surface, regenerating copy when needed.
A product is a target buyer plus a selection of blocks behind one surface. These are the configurations that are live or in build today.
AI early detection for self-insured workforces — aggregate risk, never individual health data.
AI blood-test interpretation for functional-medicine practices — physician-ready reports the doctor signs.
Post-treatment recovery & monitoring for oncology patients and their caregivers. Not diagnostic.
More configurations — clinical API, research studio, caregiver, athlete, and others — are in design on the same core. See what's shipping first →