Agentic Apps · 04.02
The Anatomy of an Agentic App: From Blank Prompt to Staffed, Running Product
One end-to-end walk through what actually exists in the database and who touches it — from build_workflow to a staffed, data-backed, self-orchestrating product.
Five tables, one product
An Agentic App is not a metaphor sitting on top of a workflow — it's a specific, small set of real tables that get populated in a specific order the moment a workflow becomes an App:
| Table | Populated by | Holds |
|---|---|---|
apps | The auto-wrap, at build time | Slug, name, version, icon, owner, status, policy. |
app_members | AppStaffingService, right after | The staffed cast — exactly one operator, the rest workers, each a real agent with baked-in competence. |
app_collections / app_records | data.define_collection, as the App's workflows declare their shape | Typed data, optionally strict-schema'd. |
app_surfaces | The surface generator, from a prompt plus the collection schemas | A typed ViewNode tree per named page. |
app_contacts | Wherever a run touches a real person | The bridge from App data to the Subject/Connection primitives — and the source of the outcomes the App's own Brain learns from. |
Staffing happens once, and never blocks the App from existing
The moment an App is created, staffing runs before anything else touches it: derive a cast from the App's own name and description, classified into one of five archetypes, then for each seat either reuse an existing workspace specialist or materialize a new one with real instructions and capability tags — never an empty placeholder agent. This is idempotent (call it again on an already-staffed App and nothing changes) and deliberately non-throwing: if staffing genuinely fails, the App still exists, just degraded and unstaffed, rather than the whole creation aborting because one non-critical step hiccupped.
Continue
Not a chatbot, not a script, not a SaaS app with an AI feature bolted on. An Agentic App is durable software built from four real pillars — data, interface, orchestration, and its own Brain.
A real learning loop scoped to one App: outcomes become graded lessons, recurring lessons graduate into inherited skills — the same Brain formation path the rest of the platform uses, never a parallel system.