Financial vertical — beginner tutorial¶
Released in FCC v1.2.0. You are new to FCC and want a gentle introduction to the Financial vertical. This tutorial walks you through loading the pack, inspecting one persona, and running the simplest scenario end-to-end — no AI provider required.
The Financial pack in one paragraph¶
The finance vertical pack (at src/fcc/data/verticals/finance.yaml) contains 11 finance personas (v2.1.0) — 5 retrofitted plus 6 v1.2.0 additions for interest-rate risk modeling, LCR reporting, counterparty credit risk, sustainable finance, digital asset strategy, and independent model validation. Headline compliance frameworks: SOX, Basel III, MiFID II, IFRS 9, SR 11-7, SFDR, CSRD, MiCA.
Focus persona: FRA — Financial Risk Analyst¶
We'll anchor this tutorial on FRA, because it's the one most relevant to the beginner audience in the Financial domain.
from fcc.verticals.registry import VerticalRegistry
reg = VerticalRegistry.from_builtin()
pack = reg.get("finance")
persona = next(p for p in pack.personas if p.id == "FRA")
print(persona.name)
print(persona.risk_category or "minimal")
riscear = persona.riscear or {}
print("Archetype:", riscear.get("archetype"))
print("Role:", riscear.get("role"))
Step 1 — Load the pack¶
The VerticalRegistry auto-discovers all packs from src/fcc/data/verticals/. You never need to list them manually.
from fcc.verticals.registry import VerticalRegistry
reg = VerticalRegistry.from_builtin()
print(f"Loaded {len(reg)} packs with {sum(len(p.personas) for p in reg.all_packs())} total personas")
You should see 6 packs and 45 personas on v1.2.0.
Step 2 — Inspect FRA¶
pack = reg.get("finance")
p = next(p for p in pack.personas if p.id == "FRA")
print(f"Name: {p.name}")
print(f"Role: {(p.riscear or {}).get('role', '—')}")
print(f"Compliance frameworks: {list(p.compliance_frameworks)}")
Step 3 — Run a mock scenario¶
FCC always defaults to MockAIClient unless you explicitly set an API key, so you can run scenarios without any cost or cloud calls.
Pick the first scenario in the list, then:
You'll see persona-generated output in your terminal — all mocked, all deterministic.
What you learned¶
- Packs are auto-discovered YAML files.
- Every persona has a nested R.I.S.C.E.A.R. block you can read from Python.
- Scenarios run in mock mode by default.
Verify what you did¶
Run the vertical test suite to make sure your changes didn't break anything:
All beginner-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¶
- Notebook 26 — Vertical packs tour — same flow in an executable notebook.
- Notebook 27 — Vertical packs deep dive — longer walkthrough of healthcare as an exemplar.
- Guidebook ch25 — Industry verticals — full authoring guide for your own pack.
- Book 3 ch11 — Vertical packs at enterprise scale — architectural view.
- Streamlit vertical_explorer — interactive browser for all 6 packs.
- Research note for finance — cited standards sources behind the persona selection.