Skip to content

Medical vertical — academic tutorial

Released in FCC v1.2.0. You are teaching or studying persona-driven agent workflows and want to use the Medical pack as a case study. This tutorial connects the persona's R.I.S.C.E.A.R. specification to the underlying regulatory standards and shows how to cite them properly in classwork or publications.

The Medical pack in one paragraph

The healthcare vertical pack (at src/fcc/data/verticals/healthcare.yaml) contains 11 healthcare personas (v2.1.0) — 5 retrofitted from v1.0 plus 6 v1.2.0 additions for genomic research, clinical imaging (DICOM), telemedicine UX, population health, precision medicine strategy, and medical device software. Headline compliance frameworks: HIPAA, HL7 FHIR R5, ICD-11, IEC 62304, EU MDR, DICOM, IMDRF SaMD.

Focus persona: GMR — Genomic Medicine Researcher

We'll anchor this tutorial on GMR, because it's the one most relevant to the academic audience in the Medical domain.

from fcc.verticals.registry import VerticalRegistry

reg = VerticalRegistry.from_builtin()
pack = reg.get("healthcare")
persona = next(p for p in pack.personas if p.id == "GMR")

print(persona.name)
print(persona.risk_category or "minimal")
riscear = persona.riscear or {}
print("Archetype:", riscear.get("archetype"))
print("Role:", riscear.get("role"))

Connecting the persona to its regulatory standards

GMR (Genomic Medicine Researcher) was selected because its responsibilities map cleanly onto published standards in the medical domain. The research note at src/fcc/data/verticals/research/medical.research.md lists the exact sources.

When citing this persona in classwork or a publication, use both:

  1. The FCC framework citation (see docs/community/citation.md).
  2. The underlying standards cited in the research note.

Extracting persona constraints for comparison

A common assignment is to compare the R.I.S.C.E.A.R. constraints across several personas and argue which are regulatory versus organizational in origin.

for p in pack.personas:
    r = p.riscear or {}
    print(f"=== {p.id} — {p.name} ===")
    for c in r.get("constraints", []):
        print(f"  - {c}")
    print()

Your homework: classify each constraint as regulatory, organizational, or professional-ethical.

Generating a model card for citation

fcc model-card generate --persona GMR --output _output/cards

Model cards follow Mitchell et al. (2019) and include a bibliographic field you can cite directly.

Verify what you did

Run the vertical test suite to make sure your changes didn't break anything:

pytest tests/test_verticals.py -k "healthcare" -v

All academic-path steps in this tutorial leave your working tree unchanged — the pack YAML is read-only from your perspective. The only state that accumulates is in _output/ (scenario run traces) and docs/model-cards/ (if you regenerated cards).

Next steps