Academy · Solutions · Agentic System
The Agentic System pattern
In one line. A governed domain brain: many collections and a fleet of agents powering a whole portfolio of use cases — with governance, compliance, recommendation and reporting operating over all of it at once. You’ll be able to. Recognize when you’ve outgrown single workflows, and stand a System up in the right order: domain model first, fleet second, workflows third, facets last. Where this lives. Every pillar of
Studio— Agents, Data, Experience, Governance. A System is the pattern that uses all four at once.
What it is
An Agentic System is level 3 of the ladder. A Workflow automates one process; a System runs a domain — loan origination, compliance operations, a lending portfolio — where many processes share the same data, the same rules, and the same accountability.
Choose this shape when the workflows start overlapping: three processes reading the same collections, the same field meaning different things in different builds, auditors asking questions no single dashboard answers. Those are the signs you need one brain, not more arms.
The canonical architecture
A System is a layered stack. Read it bottom-up — that is also the build order:
L5 OUTPUT & DELIVERY decision package + provenance, findings ┐
L4 HITL confidence gate; exceptions to a human │ cross-cutting facets
L3 VALIDATION & RULES within/cross-doc checks, screening, flags │ watch every layer:
L2 AI INTELLIGENCE classify, extract, transform, confidence │ governance, compliance,
L1 INTAKE collection ingestion fires the pipeline │ recommendation, reporting
L0 PREPARATION split long files, screen for sensitive data ┘
──────────────────────────────────────────────────────────────────
THE SHARED DOMAIN MODEL — many collections + one taxonomy.
Every agent reads it; every workflow writes to it; every facet reports on it.
Worked by a FLEET of agents + shared skills.
- The shared domain model first. The collections and the taxonomy — the field dictionary every agent and rule speaks. One model, reused everywhere. Get this wrong and every layer above inherits the mistake. (D1, D3)
- A fleet, not a hero. Not one agent but many, each expert on a slice — a classifier, an income analyzer, a screener — sharing skills so common logic is written once and reused by all of them. The lending capstone below runs five specialist agents over four shared skills on exactly this principle.
- Workflows on top. Each layer’s process is a level-2 workflow — an XFlow or a mesh moving work L0 through L5. Everything you learned in the Workflow pattern applies per layer.
- Facets over everything. Governance, compliance, recommendation, reporting.
The idea that makes Systems tractable: a facet is not a separate app — it is a lens over the same domain model. Compliance is the validation rules, the screening agents and the audit trail, taken together. Reporting is pages you assemble from the card library over what those same agents produce. You build one domain model and turn on four lenses; you do not build four systems.
The facets
| Facet | What it is | Built from |
|---|---|---|
| Governance | Who may touch what — one persona per workflow role — versioned and auditable | Access & roles, versioning |
| Compliance | Rules, screening, and an immutable record | Policy & guard rails, Audit |
| Recommendation | Agents that score and decide, with provenance | Decision agents (A4) |
| Reporting | Pages you design from the card library, plus the Usage view’s activity and estimated-cost figures | Dashboards & inbox, Audit & Usage |
Governance at this scale is mostly persona work. Project Admin is a protected role that runs the whole project; alongside it you define one persona per workflow role in your domain — Underwriter, L1-Reviewer, Credit Committee — on the Personas view of Studio > Governance > Users & Access. Each persona covers the collections and lifecycle stages that role works in, the people who hold it, and which other personas it may view. The Effective policy view is read-only: it shows the access rules this project inherited and names the workspace that set them, so when one of them is not what your domain needs you know who to ask. History, Snapshots and Freeze cover the versioned half of the row.
Cost figures on Usage are estimates for watching trends. They are not billing.
Standing one up without drowning
Do not build all six layers on day one. The incremental path that works:
- Ship one workflow end to end on the shared domain model (weeks, not months).
- Add the second workflow on the same collections — resist the copy-paste fork; this is the step where the domain model earns its keep.
- Turn on the facets one at a time, compliance first if regulators are in the room.
- Package and version the whole thing when it stabilizes (B10 · Package & ship).
Worked builds
| Build | Teaches |
|---|---|
| B8 · Compliance evidence map | The compliance facet standing alone — rules to evidence to audit |
| B9 · Capstone: Lending domain brain | The full stack: domain model, fleet, layered workflows, all four facets |
Where to go next
- See the smallest facet in action: B8 · Compliance evidence map.
- The domain model’s foundations: D1 · Collections & schema and D3 · Taxonomy & lifecycle.
- Ship it to another workspace: V4 · Hubs & distribution.
Prefer learning inside the product? The same academy lives in the platform's Learn menu — every screen links to the chapter that explains it.
See the platform live