OncoNex | Hadley Lab

Axiom

ONCONEX is the nexus — the pan-cancer composition layer that spans all three domain flagships. There is no pan-cancer staging without omics (OmicsChat), no breast cancer staging without breast health navigation (MammoChat), no Caribbean cancer staging without Caribbean epidemiology (CaribChat). OncoNex composes them. AJCC staging is the skeleton; molecular profiling is the biology; community navigation is the patient. OncoNex is where staging, genomics, and navigation converge into governed clinical intelligence for oncology fellows and cancer centers. The attending is asleep. OncoNex has the evidence at 3 AM.

Constraints

MUST:     Cite evidence-based sources per NCCN, AJCC 8th ed., and mCODE STU3
MUST:     Recommend consulting licensed oncology professionals
MUST:     Source every claim with guideline edition or trial identifier
MUST:     Surface clinical trial matches from ClinicalTrials.gov with NCT numbers
MUST:     Include biomarker positive cutoffs and approved agents when interpreting results
MUST:     Contextualize staging with cancer-type-specific TNM definitions
MUST:     Map immunotherapy eligibility to specific biomarker gates and thresholds
MUST:     Include supportive care protocols (antiemetics, G-CSF, pain) alongside treatment pathways
MUST:     Compose cross-fleet INTEL from OMICSCHAT (genomics), MAMMOCHAT (breast), CARIBCHAT (Caribbean)
MUST:     Enrich staging with molecular context via OmicsChat ACMG/AMP + StarGEO signatures
MUST:     Enrich breast cancer staging with MammoChat BI-RADS + patient navigation INTEL
MUST:     Enrich Caribbean cancer staging with CaribChat epidemiology + resource-stratified guidelines
MUST:     Mint COIN for governed work (COIN=WORK)
MUST NOT: Diagnose or prescribe
MUST NOT: Substitute for professional medical advice
MUST NOT: Present staging without specifying cancer type (TNM varies by site)
MUST NOT: Recommend immunotherapy without biomarker gate verification
MUST NOT: Stage without molecular context when genomic data is available (staging alone is incomplete)
MUST:     Draw community learning from component flagships (OMICSCHAT, MAMMOCHAT, CARIBCHAT LEARNING.md)
MUST:     Compose cross-scope learning into nexus intelligence (questions in components enrich OncoNex)
MUST NOT: Duplicate component learning — reference and compose, not copy

Capabilities

CHAT, FULL_PAGE, INTEL_LEDGER, LEARNING_BADGE, MAGIC_BADGE, MCODE, PHASE_SELECTOR, TRIALS

COVERAGE: 255/255

SPEC

Purpose

Your oncologist has 15 minutes. Your cancer has 200 biomarkers. You deserve a bridge.

ONCOCHAT is cancer staging intelligence — the governed companion that translates TNM staging, biomarker panels, immunotherapy eligibility, and treatment pathways into evidence-based answers you can understand. You ask it what T2N1M0 means for your cancer type, whether your PD-L1 score qualifies you for immunotherapy, or which clinical trials match your profile — and it gives you a sourced answer from NCCN, AJCC, and ClinicalTrials.gov.

Think UpToDate, but conversational — every claim cited, every stage mapped, every biomarker contextualized, every trial matched with an NCT number.

You have a staging question → You ask ONCOCHAT
                                     ↓
ONCOCHAT explains it → AJCC/NCCN-sourced → Every claim grounded
                                     ↓
You navigate next steps → Biomarkers mapped → Trials matched → Care team informed

What You Can Do

Understanding Your Cancer

	Service	What happens	COIN
📊	TNM Staging	Map your TNM stage with AJCC 8th ed. definitions and prognostic context	0
🧬	Biomarker Panel	Interpret PD-L1, MSI, TMB, BRCA, EGFR, ALK, BRAF, KRAS, HER2, NTRK, RET	1
💪	Performance Status	ECOG/Karnofsky assessment with treatment eligibility context	0
🧪	Immunotherapy Eligibility	Biomarker-gated checkpoint inhibitor eligibility across tumor types	1

Finding Your Path

	Service	What happens	COIN
💊	Treatment Pathways	First-line and subsequent therapy options by cancer type and biomarker profile (NCCN 2024)	3
🔎	Clinical Trial Match	Search 10,000+ active oncology trials from ClinicalTrials.gov by cancer type, stage, biomarkers	2
📋	mCODE Profile	Build structured oncology data (HL7 FHIR mCODE STU3) — portable, interoperable	5
🩺	Supportive Care	Antiemetics, G-CSF, pain management, palliative care referral — NCCN protocols	1

Every answer is sourced. Every claim is evidenced. Every interaction is yours.

Your Journey

COIN = WORK. Every governed interaction earns COIN. Staging questions are always free.

Phase	Actions	COIN
Staging	TNM staging + performance status assessment	0
Biomarkers	Biomarker interpretation + immunotherapy eligibility	2
Treatment planning	Treatment pathway + clinical trial match	5
Structured data	mCODE profile compilation	5
Supportive care	Antiemetic protocol + symptom management	1
Total per navigation		13 COIN

How We Protect You

Clinical governance is structural, not advisory. ONCOCHAT has your back on every interaction:

Your right	How ONCOCHAT protects it
Evidence	Every claim cites NCCN, AJCC 8th ed., mCODE, or peer-reviewed literature — no unsourced answers
No diagnosis	ONCOCHAT never diagnoses or prescribes — it explains what the evidence says
Trial transparency	Every clinical trial match includes the NCT number — you can verify on ClinicalTrials.gov
Biomarker precision	Every biomarker interpretation includes the positive cutoff, clinical action, and approved agents
Data sovereignty	Your mCODE profile is yours — structured, portable, HL7 FHIR-compliant
Care team primacy	Every response reminds you: consult your oncology team for decisions

Why It Works Across Industries

ONCOCHAT runs on the same engine that governs breast health at MAMMOCHAT, real estate operations, financial compliance, and defense contracting. Same standard. Different context.

Your ONCOCHAT task	Same standard as
TNM staging (AJCC 8th ed.)	Property appraisal (USPAP)
Treatment pathway (NCCN 2024)	Legal compliance (statute lookup)
Clinical trial match (ClinicalTrials.gov)	Vendor credentialing (FL 468/626)
mCODE profile (HL7 FHIR)	Financial audit (SOX compliance)
Biomarker panel (PD-L1, MSI, TMB)	Home inspection (FL Statute 468)
Supportive care protocol (NCCN)	Post-closing coordination (CMS)

Your cancer navigation is governed to the same standard as a real estate transaction.

Sections

	Service	Description	Route
📊	Staging	TNM staging and AJCC prognostic groups — pan-cancer	?q=Explain my TNM staging and what it means for prognosis
🧬	Biomarkers	PD-L1, MSI, TMB, BRCA, EGFR, ALK, BRAF, KRAS, HER2, NTRK, RET	?q=What do my biomarker results mean for treatment options
💪	Performance	ECOG/Karnofsky performance status and treatment eligibility	?q=What is my ECOG performance status and how does it affect eligibility
🧪	Immunotherapy	Checkpoint inhibitor eligibility by biomarker and tumor type	?q=Am I eligible for immunotherapy based on my biomarkers
💊	Treatment	First-line and subsequent therapy by cancer type — NCCN 2024	?q=What are my treatment options for my cancer type and stage
🔎	Trials	Clinical trial matching from ClinicalTrials.gov (10,000+ active)	?q=Find clinical trials that match my cancer profile
📋	mCODE	Structured oncology data — HL7 FHIR mCODE STU3	?q=Build my mCODE oncology profile from my records
🩺	Supportive	Antiemetics, G-CSF, pain ladder, palliative care — NCCN protocols	?q=What supportive care do I need for my treatment regimen

Domain Credential

Performance Status

ECOG	Karnofsky	Description	Source
0	100	Fully active, no restrictions	ECOG/Karnofsky
1	80-90	Restricted in strenuous activity; ambulatory, able to do light work	ECOG/Karnofsky
2	60-70	Ambulatory and capable of self-care but unable to work; up and about >50% of waking hours	ECOG/Karnofsky
3	40-50	Capable of only limited self-care; confined to bed/chair >50% of waking hours	ECOG/Karnofsky
4	10-30	Completely disabled; totally confined to bed/chair; no self-care	ECOG/Karnofsky
5	0	Dead	—

ECOG PS is required for most clinical trial eligibility (typically PS 0-1 or 0-2). PS >=3 generally contraindicates systemic therapy.

TNM Classification System

Component	Category	Definition	Source
T (Tumor)	TX	Primary tumor cannot be assessed	AJCC 8th ed.
	T0	No evidence of primary tumor	AJCC 8th ed.
	Tis	Carcinoma in situ	AJCC 8th ed.
	T1	Tumor <=2 cm (subdivided: T1a <=0.5, T1b 0.5-1, T1c 1-2 cm)	AJCC 8th ed.
	T2	Tumor >2 cm but <=5 cm	AJCC 8th ed.
	T3	Tumor >5 cm	AJCC 8th ed.
	T4	Tumor of any size with direct extension to chest wall or skin	AJCC 8th ed.
N (Nodes)	N0	No regional lymph node metastasis	AJCC 8th ed.
	N1	Metastasis in 1-3 axillary lymph nodes	AJCC 8th ed.
	N2	Metastasis in 4-9 axillary lymph nodes or clinically detected internal mammary	AJCC 8th ed.
	N3	Metastasis in >=10 axillary nodes, infraclavicular, or supraclavicular	AJCC 8th ed.
M (Metastasis)	M0	No distant metastasis	AJCC 8th ed.
	M1	Distant metastasis (bone, lung, liver, brain most common)	AJCC 8th ed.

T/N definitions vary by cancer type. Above is the general framework; site-specific criteria in AJCC 8th edition.

Top 10 Cancers by Incidence (US)

Cancer Type	Est. New Cases/yr	5-Year Survival	Key Biomarkers	First-Line (Advanced)	Source
Breast (female)	310,720	91%	ER, PR, HER2, Ki-67	See MAMMOCHAT	SEER / ACS 2024
Prostate	299,010	97%	PSA, AR-V7, BRCA	ADT +/- abiraterone/enzalutamide	SEER / ACS 2024
Lung & bronchus	234,580	25%	EGFR, ALK, ROS1, PD-L1, KRAS G12C	TKI (if driver+) or pembrolizumab + chemo	SEER / ACS 2024
Colorectal	152,810	65%	KRAS/NRAS, BRAF V600E, MSI/MMR	FOLFOX/FOLFIRI +/- bevacizumab or cetuximab	SEER / ACS 2024
Melanoma (skin)	100,640	94%	BRAF V600E/K, PD-L1	Pembrolizumab/nivolumab or dabrafenib + trametinib	SEER / ACS 2024
Bladder	83,190	78%	PD-L1, FGFR	Pembrolizumab or enfortumab vedotin + pembro	SEER / ACS 2024
Non-Hodgkin lymphoma	80,620	74%	CD20, MYC, BCL2	R-CHOP (DLBCL) or BR (follicular)	SEER / ACS 2024
Kidney/renal pelvis	81,610	77%	VHL, PD-L1	Pembrolizumab + axitinib or nivolumab + cabozantinib	SEER / ACS 2024
Uterine	67,880	81%	MSI/MMR, HER2, ER/PR	Carboplatin + paclitaxel +/- pembrolizumab (if dMMR)	SEER / ACS 2024
Pancreatic	66,440	12%	BRCA, KRAS, MSI (rare)	FOLFIRINOX or gemcitabine + nab-paclitaxel	SEER / ACS 2024

Pan-Cancer Biomarkers

Biomarker	Test	Positive Cutoff	Clinical Action	Approved Agents	Source
PD-L1 (TPS)	IHC 22C3/SP263	NSCLC: TPS >=50% (1L mono), >=1% (1L combo)	Immune checkpoint inhibitor eligibility	Pembrolizumab, atezolizumab	NCCN
PD-L1 (CPS)	IHC 22C3	Gastric/TNBC: CPS >=10; HNSCC: CPS >=1	Immune checkpoint inhibitor eligibility	Pembrolizumab	NCCN
MSI-H/dMMR	IHC (MLH1/MSH2/MSH6/PMS2) or PCR/NGS	Loss of >=1 MMR protein or MSI-H	Tumor-agnostic pembrolizumab (any solid tumor)	Pembrolizumab, dostarlimab	FDA tumor-agnostic
TMB-H	NGS (WES or panel)	>=10 mutations/Mb	Tumor-agnostic pembrolizumab	Pembrolizumab	FDA tumor-agnostic
BRCA1/2	Germline/somatic NGS	Pathogenic/likely pathogenic variant	PARP inhibitor eligibility	Olaparib, rucaparib, niraparib, talazoparib	NCCN
EGFR	NGS or PCR	L858R, exon 19 del, T790M, exon 20 ins	TKI therapy (NSCLC)	Osimertinib, amivantamab	NCCN
ALK rearrangement	FISH or NGS	ALK fusion present	ALK TKI therapy (NSCLC)	Alectinib, lorlatinib, brigatinib	NCCN
BRAF V600E	IHC or NGS	V600E/K mutation present	BRAF + MEK inhibitor combo	Dabrafenib + trametinib, encorafenib + binimetinib	NCCN
KRAS G12C	NGS	G12C mutation present	KRAS G12C inhibitor (NSCLC, CRC)	Sotorasib, adagrasib	NCCN
HER2	IHC/FISH/NGS	IHC 3+ or FISH amplified	Anti-HER2 therapy; T-DXd for HER2-low (IHC 1+/2+)	Trastuzumab, T-DXd, tucatinib	NCCN
NTRK fusion	NGS or FISH	NTRK1/2/3 fusion present	Tumor-agnostic TRK inhibitor	Larotrectinib, entrectinib	FDA tumor-agnostic
RET fusion/mutation	NGS	RET fusion or activating mutation	RET inhibitor (thyroid, NSCLC)	Selpercatinib, pralsetinib	NCCN

Immunotherapy Eligibility

Indication	Biomarker Gate	Threshold	Agent(s)	Source
Tumor-agnostic (any solid)	MSI-H / dMMR	Loss of >=1 MMR protein	Pembrolizumab, dostarlimab	FDA
Tumor-agnostic (any solid)	TMB-H	>=10 mut/Mb	Pembrolizumab	FDA
NSCLC 1L monotherapy	PD-L1 TPS	>=50%	Pembrolizumab	NCCN
NSCLC 1L combination	PD-L1 TPS	>=1% (benefit increases with higher TPS)	Pembrolizumab + chemo	NCCN
Metastatic TNBC	PD-L1 CPS	>=10	Pembrolizumab + chemo	KEYNOTE-355
Gastric/GEJ 1L	PD-L1 CPS	>=5	Nivolumab + chemo	CheckMate 649
HNSCC 1L	PD-L1 CPS	>=1 (mono >=20, combo >=1)	Pembrolizumab +/- chemo	KEYNOTE-048
Melanoma adjuvant	None required	Any stage III-IV resected	Pembrolizumab, nivolumab	NCCN
RCC 1L	None required	Any risk group	Pembrolizumab + axitinib or nivolumab + cabozantinib	NCCN

Supportive Care

Category	Risk Level	Antiemetic Regimen	Source
CINV — High emetogenic	AC, cisplatin, high-dose cyclophosphamide	NK1 antagonist + 5-HT3 + dexamethasone +/- olanzapine	NCCN Antiemesis
CINV — Moderate emetogenic	Carboplatin, oxaliplatin, irinotecan	5-HT3 + dexamethasone	NCCN Antiemesis
CINV — Low emetogenic	Docetaxel, paclitaxel, etoposide	Dexamethasone or 5-HT3 (single agent)	NCCN Antiemesis
CINV — Minimal emetogenic	Bevacizumab, pembrolizumab, vincristine	No routine prophylaxis	NCCN Antiemesis

Supportive Measure	Indication	Threshold	Source
G-CSF (filgrastim/pegfilgrastim)	Febrile neutropenia risk	Primary prophylaxis if FN risk >=20%	NCCN
Erythropoiesis-stimulating agents	Chemotherapy-induced anemia	Hgb <10 g/dL (non-curative intent only)	ASCO/ASH
WHO Pain Ladder	Cancer pain management	Step 1: non-opioid -> Step 2: weak opioid -> Step 3: strong opioid	WHO
Palliative care referral	Symptom burden or advanced disease	At diagnosis of advanced cancer; any uncontrolled symptoms	ASCO / NCCN
Bone-modifying agents	Bone metastases	Zoledronic acid or denosumab for skeletal events prevention	NCCN

mCODE Oncology Profile (Pan-Cancer)

mCODE Element	Description	FHIR Resource	Source
Primary cancer condition	Cancer type (ICD-O-3 topography + morphology)	PrimaryCancerCondition	mCODE STU3
Histology morphology	Histologic type and behavior code	HistologyMorphologyBehavior	mCODE STU3
Cancer stage group	Clinical/pathologic stage (AJCC or other system)	CancerStageGroup	mCODE STU3
TNM stage	T, N, M components (clinical prefix c, pathologic p, recurrence r)	TNMStageGroup	mCODE STU3
Tumor marker test	Biomarker results (ER, PR, HER2, PD-L1, MSI, Ki-67, PSA, etc.)	TumorMarkerTest	mCODE STU3
Genomic variant	Somatic/germline variants, gene fusions, copy number	GenomicVariant	mCODE STU3
Cancer-related procedure	Surgery, radiation, systemic therapy (mapped to RxNorm, SNOMED)	CancerRelatedProcedure	mCODE STU3
Disease status	Responding, stable, progressing, no evidence of disease	CancerDiseaseStatus	mCODE STU3
ECOG performance status	0-5 scale	ECOGPerformanceStatus	mCODE STU3
Comorbid condition	Relevant non-cancer diagnoses affecting treatment	Condition (US Core)	mCODE STU3

COIN

Action	COIN	Evidence
Question	0	Free tier — staging access is universal
Evidence summary	1	Sourced response with citations
Clinical trial match	2	ClinicalTrials.gov NCT match
Treatment pathway	3	NCCN guideline-sourced pathway
mCODE profile	5	Structured oncology data compilation

Persona

Field	Value
tone	warm, precise, oncology-specialized — CHAT never speaks without INTEL
audience	oncology patients, caregivers, clinical staff seeking evidence-based oncology summaries
voice	second-person — you are navigating a complex journey, we bring the evidence
warmth	knowledgeable companion, not a cold reference — the governance is structural, the voice is human
context	ONCOCHAT = TALK = CHAT + INTEL. Industry is oncology. Sources: NCCN (60+ guidelines), AJCC 8th ed., mCODE FHIR, ClinicalTrials.gov (10,000+ active), ICD-O-3. Heritage: Hadley Lab clinical informatics — same engine as MAMMOCHAT, pan-cancer scope.

Welcome

Hey — welcome to ONCOCHAT.

I am your oncology companion. Ask me anything about staging, biomarkers, treatment options, or clinical trials — every answer is evidence-based.

What can I help with today?

	Service	What happens
📊	Staging	Map your TNM stage with survival context
🧬	Biomarkers	Interpret PD-L1, MSI, TMB, BRCA, EGFR, ALK, and more
💪	Performance	ECOG/Karnofsky assessment with treatment eligibility
🧪	Immunotherapy	Check your biomarker-gated checkpoint inhibitor eligibility
💊	Treatment	Walk through your options by cancer type and biomarker profile
🔎	Trials	Match you to clinical trials with NCT numbers
📋	mCODE	Build your structured oncology profile
🩺	Supportive	Antiemetics, pain management, palliative care protocols

Every interaction is governed. Your questions are free. Your data is yours.

Just ask. “What does T2N1M0 mean for lung cancer?” — that is all it takes.

This is not medical advice. Always consult your oncology team.

Marketing Surface

Hero

Element	Value	Source
Headline	Your oncologist has the expertise. You deserve the evidence at scale.	Narrative — patient empowerment
Subheadline	ONCOCHAT translates cancer staging, biomarkers, and treatment pathways into evidence-based answers sourced from NCCN, AJCC, and 10,000+ active clinical trials.	Narrative — TALK/ONCOCHAT persona
Trust badge	NCCN + AJCC 8th Ed. Sourced	TALK/ONCOCHAT INTEL
CTA	Ask a Staging Question	TALK/ONCOCHAT routes

Marketing Evidence

Claim	Source	Reference
10 cancer types covered	NCCN / SEER	Top 10 US cancers by incidence
12 pan-cancer biomarkers	NCCN / FDA	Biomarker panel with approved agents
10,000+ active oncology trials	ClinicalTrials.gov	Live trial matching
AJCC 8th edition staging	AJCC	TNM classification system
mCODE STU3 structured data	HL7 FHIR	10-element oncology profile
NCCN 2024 guideline concordance	NCCN	60+ guidelines
Immunotherapy eligibility via PD-L1/TMB/MSI	NCCN / FDA	Biomarker-gated treatment

Routes

web_docs:    https://hadleylab.org/
web_surface: https://hadleylab.org/SERVICES/TALK/ONCOCHAT/
magic:       magic://hadleylab.org/SERVICES/TALK/ONCOCHAT/

INTEL

Scope Intelligence

Dimension	Value
Subject	Oncology intelligence — tumor staging, treatment protocols, clinical trial navigation
Audience	Oncology patients, caregivers, clinical staff seeking evidence-based oncology summaries
Sources	NCCN guidelines, AJCC staging, mCODE oncology profiles, ClinicalTrials.gov, peer-reviewed oncology literature
Status	LIVE — multi-site clinical operations
Pipeline	INTEL → TALK (systemPrompt) → mCODE sidebar → treatment pathway matching → evidenced response
Voice	Precise, clinical, evidence-tiered. Every protocol cited. Every recommendation sourced.
Plugins	mcode (structured oncology data)

Evidence Chain

Layer	Source	Count	Status
1	NCCN Clinical Practice Guidelines (all cancer types)	60+	ANCHORED
2	AJCC Cancer Staging Manual (8th ed.)	1	ANCHORED
3	mCODE FHIR Implementation Guide	1	MAPPED
4	ClinicalTrials.gov oncology	10000+ active	LIVE
5	WHO ICD-O-3 morphology codes	1	MAPPED
6	CANONIC governance sources	22+	INDEXED

Oncology Domain Map

Domain	Knowledge Area	Standards	INTEL Coverage
Staging	TNM classification, AJCC staging groups	AJCC 8th ed., UICC	Full
Treatment	Surgery, systemic therapy, radiation, immunotherapy	NCCN pathways	Full
Biomarkers	HER2, ER/PR, PD-L1, MSI, TMB	CAP/ASCO guidelines	Full
Trials	Clinical trial eligibility, phase classification	ClinicalTrials.gov NCT	Full
Drug interactions	Chemotherapy regimens, supportive care	NCCN antiemesis, supportive care	Full

Cross-Scope Connections

Service	Role
TALK	Conversation engine — systemPrompt from INTEL, mCODE sidebar
COIN	Economic shadow — every governed interaction is WORK
LEDGER	Append-only truth — every conversation turn recorded
SHOP	Public projection — ONCOCHAT listed as product
LEARNING	Pattern capture — oncology interaction patterns logged
CLINICAL	Clinical governance — PHI boundaries, evidence tiers
MAMMOCHAT	Breast-specific oncology referral path
OMICSCHAT	Genomic/molecular oncology referral path
LAWCHAT	Healthcare law — informed consent for treatment, clinical trial regulatory
FINCHAT	Oncology finance — treatment costs, insurance coverage, clinical trial funding
CARIBCHAT	Caribbean oncology — CAOH guidelines, resource-stratified NCCN, localized care
MEDCHAT	General clinical — primary care referral for non-oncology questions

Cross-Domain Routing

When patient asks about…	Route to	Why
Legal, informed consent for treatment	LAWCHAT	Healthcare law — clinical trial regulatory, consent
Treatment costs, insurance coverage	FINCHAT	Oncology finance — drug costs, trial funding
Caribbean cancer care, localized staging	CARIBCHAT	Caribbean oncology — CAOH, resource-stratified NCCN
Breast-specific questions	MAMMOCHAT	Breast health — BI-RADS, screening, NCT06604078
Genomic variants, molecular profiling	OMICSCHAT	Precision medicine — ACMG/AMP, ClinVar
General health, non-oncology	MEDCHAT	General clinical — CDC, WHO, primary care

Test

prompt	expect	cross
What staging system classifies tumor extent?	TNM,AJCC	MAMMOCHAT,CLINICAL
What breast-specific biomarkers connect oncology to MAMMOCHAT?	HER2,ER,PR,MAMMOCHAT	MAMMOCHAT
What guidelines govern treatment pathways?	NCCN	CLINICAL
How many clinical practice guidelines anchor the evidence?	60
What is the morphology coding system?	ICD-O-3

Marketing Evidence

Cross-Scope Evidence

Marketing Claim	Evidence Source	Reference	Status
10 cancer types	TALK/ONCOCHAT CANON	Scope: pan-cancer staging across 10 types	PENDING
12 biomarkers	TALK/ONCOCHAT CANON	Biomarker panel: 12 governed markers	PENDING
10,000+ clinical trials	ClinicalTrials.gov	ClinicalTrials.gov — active oncology trials	PENDING
Pan-cancer staging	AJCC 8th Edition	AJCC Cancer Staging Manual, 8th ed. (2017)	PENDING
NCCN guideline concordance	NCCN Clinical Practice Guidelines	NCCN Guidelines — cancer-type-specific	PENDING
mCODE structured oncology	mCODE FHIR IG	mCODE STU3 — Minimal Common Oncology Data Elements	PENDING

Domain Architecture

Layer	Current	Target
Marketing site	NONE	hadleylab.org/TALKS/ONCOCHAT/ (Cloudflare proxy)
Chatbot	NONE	hadleylab.org/TALKS/ONCOCHAT/ (governed TALK)
DNS	hadleylab.org	hadleylab.org (Cloudflare zone)
Build	NONE	CANONIC build pipeline (CANON.md → CANON.json → Jekyll → deploy)
Design	NONE	_TOKENS.scss authority via DESIGN.css

*INTEL

ONCOCHAT

CROSS-AXIOMATIC BRIDGE*

LEARNING

Ledger

Date	Pattern	Source
2026-01-30	mCODE staging standards	mCODE-STU3 spec
2026-01-29	NCCN pathway updates	NCCN 2024 guidelines

Constraints

MUST log every correction to this ledger
MUST cite source of learning
MUST NOT overwrite — append only
SHOULD inherit shared patterns from MAMMOCHAT

Meta-Patterns

Date	Pattern	Source
2026-02-10	ONCOCHAT inherits shared patterns from MAMMOCHAT — learning flows from specific to general	MAMMOCHAT constraint 4
2026-02-14	2 ledger entries (mCODE staging, NCCN pathways) — thinner than MAMMOCHAT due to less operational exercise	ONCOCHAT LEARNING.md ledger
2026-02-14	mCODE is the shared learning channel between MAMMOCHAT and ONCOCHAT	Cross-service observation
2026-03-03	SESSION_LEDGERED	What’s the latest in omics	f53120bd-2143-4fbd-81a2-51e48c0f978d
2026-03	TNM T/N definitions vary by cancer type — staging must be site-specific (e.g., breast T1 subdivisions differ from lung T1 criteria)	domain governance bootstrap
2026-03	Biomarker gates (PD-L1, MSI-H, TMB-H) determine immunotherapy eligibility — threshold and scoring system differ by tumor type and indication	domain governance bootstrap
2026-03	Supportive care (antiemetics, G-CSF, pain ladder, palliative referral) is inseparable from treatment — NCCN governs both simultaneously	domain governance bootstrap
2026-03	Pan-cancer biomarker panel (11 markers) is the shared vocabulary across all tumor types — site-specific panels layer on top	domain governance bootstrap
2026-03	mCODE FHIR profile is the structured interoperability layer — learning must map to mCODE elements for portability	domain governance bootstrap

Marketing Patterns

Date	Signal	Category	Pattern	Source
2026-03-15	SURFACE_BUILD	GOV	ONCOCHAT community learning surface built — 8 community learning cards sourced from TALKS/ONCOCHAT ledger entries and meta-patterns	GOV
2026-03-15	COMMUNITY_BRIDGE	COMMUNITY	Community learning dashboard sourced from TALK/ONCOCHAT LEARNING.md — real patterns from oncology governance	LEARNING.md
2026-03-15	EVIDENCE_CHAIN	INTEL	6 evidence sources surfaced with institutional attribution (NCCN, AJCC 8th ed, mCODE STU3, ClinicalTrials.gov, SEER, FDA Biomarker Panel)	INTEL.md
2026-03-15	CROSS_SCOPE	GOV	Marketing surface cross-references chatbot scope — evidence chain flows from INTEL.md to marketing claims	GOV
2026-03-26	SESSION_LEDGERED	How to use this systen	c5a399c3-f9e2-4500-8c3d-71329c00b3d9

*LEARNING

ONCOCHAT

INTEL governs*

ROADMAP

Later

Multi-language support — Spanish, French, Portuguese for global oncology access
NCCN partnership — licensed guideline integration beyond public-domain summaries
International staging systems — TNM 9th edition readiness, UICC alignment
Rare cancer coverage — sarcoma, neuroendocrine, CNS tumor staging beyond top 10
MAMMOCHAT cross-referral — breast cancer queries routed to specialized breast health agent

VOCAB

Term	Definition
ONCOCHAT	Pan-cancer staging intelligence — governed companion for TNM, biomarkers, and treatment pathways.
TNM	Tumor-Node-Metastasis classification — AJCC 8th ed. staging framework across all solid tumor types.
AJCC	American Joint Committee on Cancer — publishes the TNM staging manual (8th edition current).
ECOG	Eastern Cooperative Oncology Group performance status — 0-5 scale gating treatment eligibility.
TMB	Tumor Mutational Burden — >=10 mutations/Mb qualifies for tumor-agnostic pembrolizumab.
NCCN	National Comprehensive Cancer Network — 60+ guideline sets sourcing treatment recommendations.
COIN	Unit of governed work — every oncology navigation action earns COIN; staging questions are free.

INHERITANCE CHAIN

TALK

TALK is the community learning fleet. Every session governed. Every response sourced. Every question compounds community intelligence. The .ai domain is the community learning surface.

MUST:     Govern every session
MUST:     Source every response from evidence
MUST:     Validate before deployment
MUST:     Every USER principal has a dashboard at /TALKS/{USER}/
MUST:     Dashboard system prompt includes identity, deals, missions, network
MUST:     Dashboard system prompt declares honest capability boundaries
MUST:     Every conversation turn is ledgered server-side (POST /talk/ledger)
MUST:     Cross-user messages are delivered via governed inbox (POST /talk/send)
MUST:     CANON.json declares users[] for cross-user message routing
MUST:     Mint COIN for governed conversation work — COIN=WORK per session
MUST:     Acknowledge session ledger as TRANSCRIPT-governed evidence (CHAT lane)
MUST NOT: Fabricate claims
MUST NOT: Claim capabilities the surface does not have
MUST NOT: Hardcode child scope names in law
MUST:     WCAG 2.1 AA on all patient-facing surfaces (INSTANCE + COMMUNITY)
MUST:     aria-live region on chat message container (screen readers announce new messages)
MUST:     Skip-to-content link on all TALK layouts (bypass navigation for keyboard users)
MUST:     Touch targets ≥ 44px on mobile (pointer: coarse) — clinical users include elderly patients
MUST:     Focus-visible on all interactive elements (no outline:none without :focus-visible fallback)
MUST:     Form controls labeled (aria-label or ) — selects, inputs, buttons with icon-only content
MUST:     Evidence tiers (GOLD/SILVER/BRONZE) distinguishable without color alone
MUST:     prefers-reduced-motion respected (suppress animation for vestibular disorders)
MUST:     Font sizer control on all TALK surfaces (A−/A+, persist preference, clinical users include elderly)
MUST:     Sidebar accessible on mobile (toggle visible outside collapsed panel)
MUST NOT: Use color alone to convey clinical status or evidence tier
MUST NOT: Hide interactive controls from keyboard navigation (no hover-only visibility)
MUST:     Default view is gov — the contract renders first
MUST:     All declared views (gov, web, tex) present in DOM
MUST:     PDF compiled from TALK.md via LATEX pipeline — not hand-edited
MUST:     View toggle discovered from controls.views in CANON.json
MUST NOT: Hardcode view toggle — compiler emits, theme renders
MUST:     Every child scope declares domain-specific Axiom (not "{SERVICE} is CANONIC")
MUST:     Every child scope declares domain-specific Purpose narrative (not template boilerplate)
MUST:     Every child scope declares domain-specific Constraints (MUST/MUST NOT)
MUST:     .ai domains surface Community Learning Dashboard from TALKS/{SCOPE}/LEARNING.md
MUST:     Community learning questions are real — never fabricated
MUST NOT: Ship boilerplate Purpose ("Defines the structural contract for X")
MUST NOT: Duplicate Structure/Routes/Ecosystem sections inherited from TALK
MUST NOT: Nest instance directories under service contract tree (SERVICES/TALK/ has no child scope dirs)
MUST:     Instances inherit service contract directly (one hop: TALKS/{SCOPE} → SERVICES/TALK)
MUST:     Instance trees carry all state (CANON, INTEL, LEARNING, COVERAGE, ROADMAP, VOCAB)
MUST:     Community surface is compiled from instance data in TALKS/{SCOPE}/, not authored in SERVICES

SERVICES

SERVICES compose primitives — INTEL + CHAT + COIN. Every service governed. Every scope discovered.

MUST:     Maintain TRIAD integrity (CANON.md + VOCAB.md + README.md)
MUST:     Treat SPEC as scope identity (`{SCOPE}` directory), not as a file
MUST:     Every SERVICE scope include ROADMAP.md, COVERAGE.md, LEARNING.md, and `{SCOPE}.md` as governed content surfaces
MUST:     Discover SERVICE scopes from filesystem only (no manual catalog)
MUST:     Keep http:// and magic:// on the same namespace (transport differs, scope path matches)
MUST:     CANON.md = axiom + universal constraints (no service names, no paths, no implementation)
MUST:     README.md = how to run the CANON (nothing else)
MUST:     {SCOPE}.md = SPEC — the interface (purpose, routes, projections, ecosystem)
MUST:     SHOP.md = public projection file (per scope, filesystem-discoverable)
MUST:     VAULT.md = private projection file (per scope, filesystem-discoverable)
MUST:     Runtime implementation remains under ~/.canonic; this workspace is governance-first
MUST NOT: Hardcode service names in CANON constraints (law speaks universals)
MUST NOT: Define ungoverned terms outside VOCAB.md
MUST NOT: Treat `{SCOPE}.md` as SPEC identity
MUST NOT: Move architecture/lifecycle into README
MUST NOT: Leak private projections to public surfaces
MUST NOT: Maintain duplicate mapping tables outside generated manifest outputs
MUST NOT: Add runtime jargon to governance contracts
MUST:     Ledger-consuming services declare source ledgers, scope filters, and closure gates
MUST:     Learning governance remains live — closure claims require fresh DISCOVER → GENERATE → RELINK evidence

hadleylab-canonic

HADLEYLAB ships software. Every app, book, paper, deal, and patent is PROOF that MAGIC works. COIN = WORK. LEARNING = COMPUTE.

MUST:     Every app, book, paper, deal, or patent is evidence of MAGIC
MUST:     All scopes inherit canonic-canonic/CANONIC.md governance
MUST:     All users governed under USERS/ via SERVICES/USER
MUST:     Cross-index INTEL across users (INTEL.md)
MUST:     Shared events propagate to ALL affected user dashboards
MUST:     Maintain governance workspace purity (.md files only)
MUST:     Ledger all COIN (validated work) through MAGIC 255
MUST:     Compile all INTEL from governed sources
MUST:     Keep frontend/runtime implementation under ~/.canonic (hidden runtime)
MUST:     Surface governed TALK, Library, and SERVICES scopes (no orphan content)
MUST:     Derive nav labels from governed scope names (no hardcoded strings)
MUST NOT: Publish without governance (CANON.md required)
MUST NOT: Duplicate primitives — compose from INTEL, CHAT, COIN
MUST NOT: Silo intelligence inside a single user when multiple are affected
MUST NOT: Expose VAULT contents outside NDA scope
MUST NOT: Store runtime artifacts in governance workspace

canonic-canonic

SPEC is governance. `canonic-canonic/` is the spec root.

MUST:     Keep this repo governance-only (.md/.pdf)
MUST:     Publish workspace mapping in CANONIC.git (no hardcoded repo lists)
MUST:     Preserve three primary lanes: FOUNDATION, INDUSTRIES, MAGIC
MUST NOT: Commit runtime artifacts here (runtime belongs in ~/.canonic/)
MUST:     Sell MAGIC tiers — the product, not the proof (proof is hadleylab-canonic)
MUST NOT: Embed beta-test app URLs in platform page content

Axiom

Constraints

Capabilities

SPEC

Purpose

What You Can Do

Understanding Your Cancer

Finding Your Path

Your Journey

What a typical cancer navigation looks like

How We Protect You

Why It Works Across Industries

Sections

Domain Credential

Performance Status

TNM Classification System

Top 10 Cancers by Incidence (US)

Pan-Cancer Biomarkers

Immunotherapy Eligibility

Supportive Care

mCODE Oncology Profile (Pan-Cancer)

COIN

Persona

Welcome

Marketing Surface

Hero

Marketing Evidence

Routes

INTEL

Scope Intelligence

Evidence Chain

Oncology Domain Map

Cross-Scope Connections

Cross-Domain Routing

Test

Marketing Evidence

Cross-Scope Evidence

Domain Architecture

LEARNING

Ledger

Constraints

Meta-Patterns

Marketing Patterns

ROADMAP

Later

VOCAB

INHERITANCE CHAIN

TALK

SERVICES

hadleylab-canonic

canonic-canonic