Skip to content
Analysis & evidence

Analysis & evidence

You ask a question on Ask. FACE reads your connected sources and answers it, shows what you could do about it on Options, the rules and sources behind it on Why, and the actions it drafted on Actionable Twins, where a named person approves or rejects each one. This section explains how each of those results is produced and how to read it.

It is written for evaluators who need to decide whether those outputs can be trusted, so every statement here is taken from the backend code and its protobuf contract (semantics.v1), and names the RPC, field or variable it describes.

Two rules that shape everything here

Sovereign inference only. Every text, vision and voice call goes to an OpenAI-compatible model plane served inside the FACE deployment’s own cluster (Runink’s shared machines on a Trial, your own cloud on Cloud, your own servers on On-premises). FACE never calls an outside AI service on any plan, and it ships no model server of its own. If the plane is not configured, FACE refuses to start instead of running with nothing behind it. See Sovereign models.

Determination is separate from expression. Any output that a third party might act on, such as an evidence document or a remediation order, is built in two layers:

  • Determination is fixed arithmetic over cited records. No model is involved.
  • Expression is optional prose that a model may draft, but only after the determination is frozen.

The contract states it in one line: the model never decides what is true; it only phrases what was decided. See Evidence documents.

The pipeline at a glance

    flowchart LR
    A[Connected sources] -->|allowlisted reads| B[Extract & profile]
    B --> C[Cluster & EDA<br/>HDBSCAN · Prophet/ARIMA]
    C --> D[Phase 1<br/>posture + rules]
    D --> E[Phase 2<br/>hypothesis swarm]
    E --> F[Phase 3<br/>twins decision]
    F --> G[Judging ladder]
    G --> H[Action cards +<br/>evidence documents]
    H --> I{Actionable Twins<br/>approve / reject}
    I -->|approve| J[Seal chained into<br/>append-only lineage log]
    K[(Tenant corpus<br/>plain text, DCI)] -.grounding.-> D & E & F
  

Pages in this section

Reading the results

Every page ends with a Reading the results note: what a result shows, and what stays with the person who acts on it. Throughout the contract, FACE puts the difference between “measured zero” and “not measured” on the wire, not in prose. You’ll see this in fields such as EvaluationMetrics.unmeasured_reason, FetchAnalysisResult.hypothesis_swarm_ran, AbsentFigure.reason, IngestSurveillanceFeedResponse.detection_note and AnalyzeEstateCausalResponse.answered. A client that shows a number should read its companion field first.

Connecting sources is covered in Data sources. Transport, identity and at-rest encryption are covered in Security. Full message definitions are in the API reference.