Clarity

Section 01

Venture Overview

Clarity is a health navigation companion that guides young adults through the complexity of the American healthcare system — entering at the moment of highest confusion: first open enrollment at a new employer.

Problem

Health system complexity + learned helplessness at first independent enrollment

User

Young adults entering the workforce — first job, first time choosing their own plan

Entry Point

Open enrollment window — 2–3 weeks, no extensions, maximum confusion

Product

App-first companion + on-demand human consultant for high-stakes moments

Business Model

B2B2C — employer pays, employee trusts. Structurally independent from employer

Moat

Structural privacy firewall — health data never touches employer systems

Section 02

Knowledge Graph — 100 Triples

Clarity's intelligence is powered by a 100-triple domain knowledge graph organized into 5 entity clusters plus 15 cross-cluster reasoning chains. The graph is user-centered — every entity exists in relation to one specific person's situation.

👤

User

Triples 1–5

📋

Insurance

Triples 6–25

🏥

Care System

Triples 26–45

💊

Health Events

Triples 46–65

💰

Financial

Triples 66–85

🔗

Cross-Cluster

Triples 86–100

👤 User — Triples 1–5

#	Entity A	Relationship	Entity B
1	User	HAS	Insurance Plan
2	User	EARNS	Income Bracket
3	User	LIVES_IN	Location
4	User	HAS_CONDITION	Health Status
5	User	CAN_AFFORD	Monthly Premium

📋 Insurance Plans — Triples 6–25

#	Entity A	Relationship	Entity B
6	Insurance Plan	HAS_TYPE	HMO
7	Insurance Plan	HAS_TYPE	PPO
8	Insurance Plan	HAS_TYPE	HDHP
9	Insurance Plan	HAS_COST	Monthly Premium
10	Insurance Plan	HAS_COST	Deductible
11	Insurance Plan	HAS_COST	Copay
12	Insurance Plan	HAS_COST	Coinsurance
13	Insurance Plan	HAS_LIMIT	Out-of-Pocket Maximum
14	Insurance Plan	INCLUDES	In-Network Providers
15	Insurance Plan	EXCLUDES	Out-of-Network Providers
16	Insurance Plan	REQUIRES	Primary Care Physician
17	Insurance Plan	COVERS	Preventative Care
18	Insurance Plan	COVERS	Mental Health
19	Insurance Plan	COVERS	Prescriptions
20	Insurance Plan	COVERS	Emergency Care
21	Employer	CONTRIBUTES_TO	Monthly Premium
22	Employer	SETS	Enrollment Window
23	Employer	DEFINES	Waiting Period
24	HDHP	PAIRS_WITH	HSA Account
25	User	SELECTS	Insurance Plan

🏥 Care System — Triples 26–45

#	Entity A	Relationship	Entity B
26	Care System	HAS_PROVIDER	Primary Care Physician
27	Care System	HAS_PROVIDER	Specialist
28	Care System	HAS_PROVIDER	Urgent Care
29	Care System	HAS_PROVIDER	Emergency Room
30	Care System	HAS_PROVIDER	Telehealth
31	Primary Care Physician	SERVES_AS	First Point of Contact
32	Specialist	REQUIRES	Referral (HMO)
33	Urgent Care	COSTS_LESS_THAN	Emergency Room
34	Telehealth	IS_COVERED_BY	Most Modern Plans
35	Visit Type	HAS_CATEGORY	Preventative
36	Visit Type	HAS_CATEGORY	Acute
37	Preventative Visit	IS_FREE_UNDER	ACA Guidelines
38	Acute Visit	TRIGGERS	Copay
39	Emergency Room Visit	TRIGGERS	Deductible
40	Provider	HAS_STATUS	In-Network
41	Provider	HAS_STATUS	Out-of-Network
42	In-Network Provider	COSTS_LESS_THAN	Out-of-Network Provider
43	HMO Plan	REQUIRES	Referral for Specialist
44	PPO Plan	ALLOWS	Direct Specialist Access
45	User	SHOULD_VERIFY	Network Status Before Visit

💊 Health Events — Triples 46–65

#	Entity A	Relationship	Entity B
46	Health Event	HAS_TYPE	Preventative
47	Health Event	HAS_TYPE	Acute
48	Health Event	HAS_TYPE	Chronic
49	Preventative Event	PREVENTS	Acute Crisis
50	Annual Physical	IS_COVERED_AT	Zero Cost (ACA)
51	Blood Panel	DETECTS	Early Risk Indicators
52	Early Risk Indicator	TRIGGERS	Preventative Action
53	Preventative Action	COSTS_LESS_THAN	Crisis Treatment
54	Acute Event	TRIGGERS	Unplanned Spending
55	Mental Health Episode	IS_COVERED_BY	Modern Insurance Plans
56	Chronic Condition	REQUIRES	Ongoing Care Plan
57	Chronic Condition	INCREASES	Annual Healthcare Cost
58	Life Stage Trigger	REQUIRES	Insurance Re-evaluation
59	New Job	IS_A	Life Stage Trigger
60	Aging Out of Parent Plan	IS_A	Life Stage Trigger
61	Moving to New City	AFFECTS	Provider Network Access
62	EOB Received	REQUIRES	Plain Language Translation
63	Lab Result	REQUIRES	Contextual Explanation
64	Enrollment Window	HAS_DURATION	2–3 Weeks
65	User	EXPERIENCES	Life Stage Trigger

💰 Financial — Triples 66–85

#	Entity A	Relationship	Entity B
66	Financial Document	HAS_TYPE	EOB
67	Financial Document	HAS_TYPE	Medical Bill
68	EOB	IS_NOT	Medical Bill
69	EOB	SHOWS	What Insurance Paid
70	Medical Bill	SHOWS	Patient Responsibility
71	Itemized Bill	CONTAINS	CPT Codes
72	CPT Code	REQUIRES	Plain Language Translation
73	Surprise Bill	VIOLATES	No Surprises Act (2022)
74	Patient Responsibility	EQUALS	Bill Minus Insurance Payment
75	User	HAS_RIGHT	Request Itemized Bill
76	Hospital	OFFERS	Financial Assistance Program
77	Financial Assistance	IS_UNKNOWN_TO	Most Patients
78	HSA	REQUIRES	HDHP Enrollment
79	HSA	PROVIDES	Triple Tax Advantage
80	FSA	HAS_RULE	Use It or Lose It
81	Medical Debt	CAN_AFFECT	Credit Score
82	Payment Plan	IS_AVAILABLE_AT	Most Hospitals
83	Payment Plan	IS_UNKNOWN_TO	Most Patients
84	User	SHOULD_NEGOTIATE	Medical Bill
85	Clarity	TRANSLATES	Financial Document → Plain Language

🔗 Cross-Cluster Reasoning — Triples 86–100

#	Entity A	Relationship	Entity B
86	User (healthy, low income)	SHOULD_SELECT	HDHP + HSA
87	User (chronic condition)	SHOULD_SELECT	PPO
88	User (new city)	MUST_REVERIFY	In-Network Providers
89	Life Stage Trigger	INITIATES	Full Plan Re-evaluation
90	Preventative Visit	REDUCES	Long-Term Financial Risk
91	Unmet Deductible	AFFECTS	Cost of Acute Visit
92	HSA Balance	OFFSETS	Out-of-Pocket Cost
93	Out-of-Network Visit	GENERATES	Surprise Bill Risk
94	Surprise Bill	TRIGGERS	No Surprises Act Protection
95	Mental Health Visit	IS_COVERED_EQUALLY	Physical Health Visit
96	Annual Physical	PREVENTS	Undetected Chronic Condition
97	Undetected Chronic Condition	INCREASES	Medical Debt Risk
98	Employer	FUNDS	Clarity Access
99	Clarity	BUILDS	User Health Literacy Over Time
100	Health Literate User	COSTS_LESS_THAN	Uninformed User (to employer)

Health Literate User COSTS_LESS_THAN Uninformed User
Triple 100 — The Business Case in One Line

Section 03 — Session 5

Entity Linking — Ontology Grounding

Entity linking proves that Clarity's knowledge graph is grounded in real-world standards — not invented terminology. Each key entity is mapped to an authoritative ontology, making the graph interoperable, verifiable, and trustworthy.

Clarity Entity	Standard / Ontology	Authority	Notes
Insurance Plan (HMO, PPO, HDHP)	HL7 FHIR Coverage Resource	HL7 International	FHIR R4 defines plan type codes used in all US payer APIs
Deductible / Premium / Copay / OOP Max	FHIR InsurancePlan.cost	HL7 / CMS	Standardized under ACA Section 1311 disclosure rules
CPT Code	Current Procedural Terminology (CPT)	American Medical Association	Required on all US medical claims; 10,000+ procedure codes
ICD-10 Diagnosis Code	ICD-10-CM	WHO / CDC	All US diagnoses mapped here; mandatory for billing
Primary Care Physician / Specialist	SNOMED CT	SNOMED International	Clinical role taxonomy; also in NPI Registry (CMS)
Health Status / Chronic Condition	SNOMED CT + ICD-10	WHO / SNOMED International	SNOMED for clinical terms; ICD-10 for billing classification
Preventative Visit / Annual Physical	USPSTF Guidelines	US Preventive Services Task Force	ACA mandates zero-cost coverage for A/B rated services
HSA / FSA / HRA	IRS Publication 969	Internal Revenue Service	Federal tax code defines eligibility, contribution limits, rules
Surprise Bill	No Surprises Act (2022)	US Federal Law (CMS)	Prohibits balance billing; dispute resolution process defined
EOB (Explanation of Benefits)	FHIR ExplanationOfBenefit Resource	HL7 / CMS	CMS requires machine-readable EOBs under Interoperability Rule
Mental Health Parity	Mental Health Parity and Addiction Equity Act	US Federal Law (DOL/HHS)	Requires equal coverage for mental + physical health
In-Network / Out-of-Network	FHIR Network Resource	HL7 / CMS	Plan network data now available via CMS Price Transparency Rule
User Location	FHIR Patient.address	HL7 International	ZIP-level data affects plan availability and provider network
Lab Result / Blood Panel	LOINC (Logical Observation Identifiers)	Regenstrief Institute	Universal standard for lab tests and clinical observations
Enrollment Window	45 CFR Part 155 (ACA Regulations)	HHS / CMS	Federal regulation defines SEP and OEP timelines

Why This Matters for Clarity

Clarity's AI doesn't invent health information — it traverses grounded triples.
Every entity links to a federal standard, clinical ontology, or legal framework.
This is what makes Clarity's guidance trustworthy — not just plausible.

Section 04 — Session 5

AI Reliability Analysis

Where will Clarity's AI get things wrong — and what happens when it does? This analysis maps the highest-risk failure modes, their triggers, and the mitigation architecture built into Clarity's design.

Failure Mode	How It Happens	Severity	Mitigation
Plan Recommendation Error	AI recommends HDHP to user with undiagnosed chronic condition — based on incomplete health history	Critical	Human consultant escalation for any recommendation involving chronic risk; disclaimer on all plan suggestions
Network Status Hallucination	AI states a provider is in-network based on stale training data — user gets surprise bill	Critical	Real-time FHIR network API lookup required; no static assertions about network status
CPT Code Mistranslation	AI translates CPT code incorrectly — user believes they were billed for wrong procedure	High	CPT translations sourced from AMA database, not LLM generation; human review for disputed bills
State-Specific Rule Errors	AI applies federal ACA rules without accounting for state-level variation in Medicaid, mandates, or plan types	High	User.location entity used to route to state-specific rule layer; 50-state regulatory index required
Financial Assistance Gaps	AI fails to surface hospital charity care programs because they are not in training data	High	RAG pipeline with live hospital financial assistance database; not LLM parametric knowledge
Confident Hedging on Legal Rights	AI softens user's legal rights (No Surprises Act, itemized bill right) to avoid sounding prescriptive	High	Legal rights stored as hard assertions in KG — not LLM-generated; output templated not generated
Deductible Math Errors	AI miscalculates remaining deductible, OOP max, or HSA contribution limit	High	Financial calculations handled by deterministic code, not LLM; LLM only provides explanation layer
Emotional Tone Mismatch	AI delivers bad news (high bill, denied claim) with incorrect emotional register — too clinical or too casual	Medium	Tone calibration layer in prompt architecture; human consultant available for high-stress moments

Clarity's AI Safety Architecture — Three Layers

Layer 1 — Grounded KG: All factual assertions sourced from ontology-linked triples, not LLM parametric memory
Layer 2 — Deterministic Logic: Financial calculations, legal rights, network status = code, not generation
Layer 3 — Human Escalation: Any recommendation involving chronic conditions, disputed bills, or denied claims → human consultant

The rule: AI explains. Humans decide.
Clarity never tells you what to do — it gives you what you need to choose.
AI Reliability Principle — Clarity v1.0

Section 05

What We Don't Know — Risk Analysis

The knowledge graph and AI architecture are strong. These are the open questions that still need answers before Clarity ships.

#	Open Question	Impact	Mitigation Path
1	Will young adults trust an employer-funded health app with their personal data?	Core trust architecture assumption	Structural privacy firewall; independent data store; explicit user consent flow
2	Does giving personalized plan recommendations trigger insurance advisor licensing?	Legal/regulatory exposure	Legal review; "guidance not advice" framing; human consultant as licensed layer
3	How do we handle 50-state insurance regulation variation at scale?	Knowledge graph completeness	State-specific regulatory layer; location-aware routing in KG
4	What happens when Clarity's recommendation conflicts with the employer's cheapest plan?	Structural independence test	Fiduciary-like duty to user written into employer contract language
5	Can we source and scale high-quality on-demand health consultants?	Human layer quality + liability	Credentialing framework; scope of practice guidelines; malpractice clarity