Getting Started (Policy Makers)¶
This page is a zero-prerequisite orientation. You will not write code. By the end you will have a shared vocabulary with the technical team, a mental model of what an FCC system does, and a checklist for your first policy-relevant conversation.
The one-minute summary¶
FCC stands for Find, Create, Critique. It is a framework for building AI systems that behave like multi-disciplinary human teams: a "Finder" agent surfaces relevant context, a "Creator" agent drafts output, and a "Critique" agent scrutinizes the draft against a specification. Each agent role is defined by a persona — a YAML document with ten structured fields (the R.I.S.C.E.A.R. spec). Personas carry explicit constraints, responsibilities, and risk tags, which is what lets a policy reviewer audit the system at all.
A deployment might include 5 personas or 164. The current canonical catalog ships 164 personas across 20+ categories (core, integration, governance, stakeholder, champion, ML lifecycle, data engineering, DevOps, UX, and six full vertical packs).
Why the three-step cycle matters for policy¶
Single-agent AI systems (one prompt, one LLM, one answer) are hard to audit because all the reasoning happens inside an opaque model call. The Find → Create → Critique cycle externalizes the reasoning into at least three inspectable steps, each with its own persona, constraints, and logged output. From a policy standpoint, this is closer to the separation-of-duties pattern familiar from financial controls: the person drafting is not the same person checking.
Key objects you will encounter¶
- Persona (YAML file) — defines a role. Example categories:
ml_lifecycle,governance,healthcare,finance. The YAML includes arisk_categoryfield (minimal / limited / high / unacceptable) that drives compliance routing. - Scenario — a JSON file describing a single FCC run: which personas participate, what the input is, which workflow graph executes.
- Workflow graph — a directed acyclic graph of steps. FCC ships seven canonical graphs ranging from 5 to 84 nodes.
- Compliance report — a JSON artifact emitted after an audit. Contains findings, evidence, remediation status.
- Model card — a Markdown document (one per persona) with responsibilities, constraints, known limitations, intended use.
A small example¶
Imagine a municipal government uses FCC-based Crater (the legal-vocabulary constellation-vertical) to triage citizen requests for public records. The deployment runs three personas:
- A Finder tagged
risk_category: limitedthat retrieves the relevant statute and precedent. - A Creator tagged
risk_category: limitedthat drafts a response. - A Critique tagged
risk_category: highthat checks the draft against redaction rules and citizen-privacy constraints.
The deployment's overall risk posture is high (the maximum of its parts). The compliance report must therefore include every Article 9-15 requirement from the EU AI Act. The model cards for the three personas are delivered to the municipal legal counsel before go-live.
Even if you never read the source code, you can understand the deployment at this level of description — and that is enough to draft a procurement clause, an oversight resolution, or a constituent-facing FAQ.
What you can ask the technical team¶
Here is a ready-made checklist of questions that produce policy-useful answers:
- "What is the highest
risk_categoryamong the personas in this deployment?" - "Can I see the compliance report from the last audit? (JSON is fine.)"
- "Which persona in this deployment has the
responsibilitiesfield that mentions the decision I'm worried about?" - "Which EU AI Act articles are flagged as non-compliant or partial?"
- "Is there a NIST AI RMF crosswalk? (There should be — 29 subcategories are mapped.)"
- "What vertical pack does this deployment inherit from?" (Answers: healthcare, finance, legal, insurance, energy, government — or none.)
What you should not worry about (yet)¶
- Model weights. Policy usually does not need to touch them; the model card describes them.
- Python package internals. The
src/fcc/tree is engineering-owned. - Plugin code. Plugins produce evidence you can read without caring how they were built.
Where next¶
Proceed to Audit Primer to learn how to read a compliance report end-to-end. If you want the shortest possible path to producing a brief, skip to Policy Brief Generation. Definitions live in Ecosystem Glossary.