aidentity / index

agentii-ai/agentii-investment-intelligence · Apache-2.0

med-market-sizing

Patient-flow market sizing for med products — prevalence → diagnosed → interested → affordable → covered → treated → persistent, priced as price × duration per cohort, with capacity constraints, named historical analog anchoring, and always bull/base/bear named-driver grids. Use to size a therapy area or product market before any valuation or share work.

stable

Contents

> Methodology inspired by publicly taught patient-flow sizing approaches; all text is an original paraphrase.

Defaults

ParameterDefault ValueRationale
funnel_stages7prevalence → diagnosed → interested → affordable → covered → treated → persistent
affordability_rule~10% monthly budgetIncome-share rule per cohort and country
scenario_gridbull/base/bearNever a single point number
analog_anchorsnamedStatins for penetration, tech S-curves for adoption
capacity_stateexplicitSupply-constrained vs demand-limited + flip condition

Preflight

Run canonical pre-flight per contracts/preflight.md. Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md — carry the _run_id from your first tool result and name yourself (and your parent, if you were spawned). Confirm ticker resolution via search_companies before market queries.

Triggers

  • "What is the TAM for [therapy area]?"
  • "Size the market for [drug/device] in [indication]."
  • "What has to be true for the bear case in [class]?"
  • "Walk me through the patient funnel for [indication]."
  • "Is [class] supply-constrained or demand-limited?"
  • "What capacity ceiling do [company]'s plants impose?"
  • "Anchor [class] adoption to a historical analog."
  • "Bull/base/bear sizing for [indication] with drivers."
  • "How does the income-share rule cap affordability?"
  • "What penetration rate is realistic for [class]?"
  • "How much API does [class] need per patient-year?"

Production Grounding

  • Funnel: prevalence → diagnosed → interested → affordable (income-share rule, ~10% of monthly budget) → covered → treated → persistent; every stage carries an explicit rate or a coverage_gap. Price as price × duration per cohort and country; never skip a stage silently.
  • Capacity check is mandatory: plants × units/yr, API kg/patient/yr, fill-finish lead times. State whether the market is supply-constrained or demand-limited and the condition that flips it.
  • Analog anchoring: named historical analogs (statins for penetration, tech S-curves for adoption); every anchor carries its citation.
  • Scenario discipline: bull/base/bear with a named-driver assumption grid; uncertainty at market level, POS at asset level; model-vs-consensus delta always explicit; abstain where unquantifiable.
  • Badges: [FACT]/[DEDUCTED]/[VIEW] with the summary table.

Data Source Priority

  1. Prevalence/epidemiology: search_documents (epidemiology sources) + read_source_outline / read_source_pages.
  2. Universe + mechanism: search_universe_drugs / search_universe_devices; search_drug_knowledge / search_drugs_by_indication (spec 054 silver).
  3. Pricing/coverage: search_sec_filings (net price, GTN) + payer coverage via search_documents.
  4. Capacity: filings and transcripts (plants, API supply, fill-finish).
  5. Knowledge: search_investment_strategies / search_investment_cases (sectors=med) for sizing frameworks and prior TAM cases.

Methodology

Retrieval Scope

unstructured_document_search

Retrieval Strategy
  1. Resolve indication and product scope via search_companies + search_universe_drugs / search_universe_devices.
  2. Collect prevalence/diagnosis rates from epidemiology documents; cite each stage rate.
  3. Pull pricing (net price, GTN) and coverage evidence from filings and payer documents.
  4. Pull capacity evidence (plants, API supply, fill-finish) from filings/transcripts.
  5. Anchor penetration to named analogs; retrieve prior TAM cases (sectors=med); cite /v/ records.
  6. Build the bull/base/bear grid.
Temporal Scope

See frontmatter temporal_scope block. Ramp and capacity paths may extend to max_quarters.

Tool Allowlist

See frontmatter allowed_tools.

Protocol
  1. Indication framing
  2. Funnel build (stage rates cited or coverage_gap)
  3. Cohort pricing (price × duration)
  4. Capacity check + constraint state
  5. Analog anchoring
  6. Bull/base/bear grid

Modes

  • Drug / biologic (default): prevalence-based funnel with payer/coverage stages.
  • Device: placements/procedures and installed-base stages replace script stages.
  • Vaccine: healthy-population cohorts, ACIP-gated uptake, procurement value.
  • Single indication: one indication × country with full cohort splits.

Tool Fallbacks

FailureFallback
Prevalence source absentcoverage_gap at the stage; list required inputs — never fabricate a rate
No pricing disclosureBracket net price from filings; label [DEDUCTED] / [VIEW]
Drug absent from silver layerUniverse + filings; annotate knowledge coverage_gap
Capacity undisclosedState the flip-condition logic qualitatively [VIEW]

Output File

{ticker}/{YYYY-MM-DD_HHMM}_med-market-sizing_{affix}.md (market-level: _sector/{YYYY-MM-DD_HHMM}_med-market-sizing_{affix}.md)

Output Structure

  1. Executive Summary — TAM stance + constraint state, 2-3 sentences
  2. Patient-Flow Funnel — stage-by-stage rates, each cited or coverage_gap
  3. Cohort Pricing — price × duration per cohort/country
  4. Capacity Check — ceiling + supply-constrained vs demand-limited + flip condition
  5. Analog Anchors — named penetration/adoption analogs with citations
  6. Scenario Grid — bull/base/bear with named-driver assumptions
  7. Coverage Gaps — missing sources and degraded stages

Error Handling

ErrorFallback
Missing prevalence datacoverage_gap at the stage; state the required input — never fabricate a rate
Conflicting prevalence sourcesShow both with provenance; use the range in the scenario grid
No consensus comparatorState model vs consensus as unavailable; keep the bull/base/bear internal consistency

Memory Load

See contracts/memory-load.md.

Snapshot

See contracts/snapshot-synthesis.md.

Final Summary (TUI)

Include ### Key Citations block with 0-10 clickable /v/ URLs.

References

  • contracts/citation-and-memory.md
  • contracts/output-frontmatter-schema.md
  • contracts/memory-load.md
  • contracts/snapshot-synthesis.md
  • contracts/preflight.md
  • references/knowledge-frameworks.md

Provenance

Authored by agentii-ai in agentii-ai/agentii-investment-intelligence. The content is mirrored here under its upstream license.

Related

3-statement 3-statement financial model, integrated IS BS CF, income statement projection, balance sheet forecast, cash flow statement, cross-statement balancing, financial model build, operating model, three statement model, integrated financial statements agentii-ai/agentii-investment-intelligence Apache-2.0 comps Comparable company analysis, trading comps, peer multiples, EV/EBITDA comparison, P/E benchmarking, comps table, relative valuation, industry multiples, precedent transactions, trading comparable analysis # Curated subset — provenance RECORDED 2026-09-21 (spec 058 T004/T005, FR-051). # # This value was NOT curated and reviewed. It reached the generated # `skill-registry.yaml` first, by a hand-edit of that file on 2026-09-20 (commit # `aea28b1`, "test and debug"), which put the repo red on Check 31 — the registry said # `[retrieval-scope]` while this file declared no `essentials_modes` at all. Spec 058 # then reconciled the divergence by declaring the registry's value here, which is the # declaration FR-051 asks for (the source of truth is this file; `sync-registry.sh` # regenerates the registry from it — `sync_registry.build_entries()` reads # `essentials_modes` straight from this frontmatter, so a hand-edit to the registry # cannot survive a check). # # What is still OPEN is the curation itself: nobody has judged whether # `retrieval-scope` is the right default for this skill. The kit's only documented # derivation, `essentials_modes = first <=3 modes` (scripts/mode_backfill.py), would # give `[preflight, triggers, defaults]` — this file's own document sections, not # analysis modes — which is why that derivation is not what was applied. Note the # asymmetry a reviewer should start from: `reverse-dcf` declares the SAME five modes # (`preflight, triggers, defaults, methodology, retrieval-scope`) and defaulted to # `[methodology]`, which is what `depth_to_modes`'s own fallback prefers where it # exists. Two skills, identical declared sets, different answers, no recorded reason. # Owner: whoever owns this skill's methodology. agentii-ai/agentii-investment-intelligence Apache-2.0 dcf DCF valuation model, discounted cash flow, intrinsic value, WACC calculation, terminal value, free cash flow projection, equity value per share, DCF sensitivity analysis, unlevered free cash flow, present value calculation, build a DCF agentii-ai/agentii-investment-intelligence Apache-2.0 full-equity-research The Auto 档 scenario — a soft-plan orchestrator for a complete fundamental equity research thesis: understand → financials → valuation → synthesize. The body is a soft plan (stages), not a rigid DAG; correctness is enforced by each referenced skill's own requires: preconditions, never by this plan's rigidity (Q2). agentii-ai/agentii-investment-intelligence Apache-2.0 lbo LBO model, leveraged buyout, private equity acquisition, sources and uses, debt schedule, returns waterfall, sponsor IRR, MOIC calculation, PE exit analysis, LBO valuation agentii-ai/agentii-investment-intelligence Apache-2.0