OntogonyGoverned decision systems
Publication gate: closed

Navigate

Inspect the publication gate

System

A governed decision loop, not a collection of tools

Ontogony separates mechanics, execution, model access, semantic authority, promotion, and evidence so that no single layer silently becomes the whole system.

Interactive system explanation

Inspect each authority boundary

Select a stage to keep the diagram, ownership panel, structured fallback, compact loop rail, and URL in one deterministic state.

Static system map

The governed decision loop

Responsibility moves through seven named stages, then closes through replay and offline verification. Supporting lanes cross the sequence without replacing it.

Governed decision loop topologyEight linked stages run from source intake and lineage through replay and offline verification. Stage eight sends advisory review findings back to source intake without granting promotion authority. Shared mechanics and supporting lanes cross the complete sequence. A text equivalent follows the diagram.Shared mechanics — Ontogony.PlatformCross-cutting mechanicsEvidence canonization · Vendor adapters · Deterministic test range · Workbench projectionCURRENT SUPPORTING LANESTAGE 01Source intakeComponent · MetaboleCURRENTSTAGE 02Temporal contextComponent · AisthesisCURRENTSTAGE 03Governed runComponent · AllagmaCURRENTSTAGE 04Model accessComponent · ConexusCURRENTSTAGE 05Semantic authorityComponent · KanonCURRENTSTAGE 06Promotion authorityComponent · ARGCURRENTSTAGE 07DossierComponent · ALLCURRENTSTAGE 08ReplayMethod · Offline verificationCURRENT
  1. 01Source intake and lineageComponent · MetaboleCurrent

    Lineage-bearing source material

  2. 02Temporal context and reconstructionComponent · AisthesisCurrent

    Reconstructed decision context

  3. 03Governed runComponent · AllagmaCurrent

    Governed operation and event evidence

  4. 04Controlled model accessComponent · ConexusCurrent

    Bounded model result and call record

  5. 05Semantic and policy judgmentComponent · KanonCurrent

    Judgment with cited authority

  6. 06Promotion and officializationComponent · ARGCurrent

    Promoted, denied, or held decision

  7. 07Dossier and verificationComponent · ALLCurrent

    Inspectable dossier boundary

  8. 08Replay and offline verificationMethod · Offline verificationCurrent
Advisory review returns to the loop

Current · Deterministic test range — a supporting lane outside the core decision sequence.

Required handoffAdvisory resultEvidence attachmentAdvisory review returnSupporting laneProhibited ownership

Structured fallback

Topology text equivalent

The same eight-stage sequence shown in the diagram, in reading and keyboard order.

Ordered governed decision loop and responsibility handoffs
StageResponsibilityComponentHandoffRelationship
1CurrentSource intake and lineageMetaboleLineage-bearing source materialRequired handoff
2CurrentTemporal context and reconstructionAisthesisReconstructed decision contextRequired handoff
3CurrentGoverned runAllagmaGoverned operation and event evidenceRequired handoff
4CurrentControlled model accessConexusBounded model result and call recordAdvisory result
5CurrentSemantic and policy judgmentKanonJudgment with cited authorityRequired handoff
6CurrentPromotion and officializationARGPromoted, denied, or held decisionEvidence attachment
7CurrentDossier and verificationALLInspectable dossier boundaryEvidence attachment
8CurrentReplay and offline verificationLoop closureReview findings returned to the loopAdvisory review return
Cross-cutting and supporting lanes
Shared mechanics — Ontogony.Platform
Cross-cutting mechanics used by the governed loop.
Evidence canonization — Flock
A supporting lane for multi-agent evidence handling.
Redacted evidence intake — Vendor adapters
A boundary lane for vendor and runtime evidence.
Deterministic test range — Synthetic Estate
A controlled test lane outside the core decision sequence.
Operator and buyer projection — Workbench
A projection surface, not a source of truth.

Stage 01

Source intake and lineage — Metabole

contextual

Acquires source material while preserving identity, provenance, handling context, and data-quality evidence.

Owns

  • Governed ingestion and source profiling
  • Transformation and mapping-candidate evidence
  • Source lineage and data-quality evidence

Does not own

  • Semantic truth
  • Model routing or governed execution
  • Promotion or legal determination

Receives

  • Source records and declared source context
  • Publication-approved lineage metadata

Produces

  • Lineage-bearing source material
  • Transformation and data-quality evidence

Stage 02

Temporal context and reconstruction — Aisthesis

contextual

Connects time-indexed evidence so a reviewer can understand what was known when.

Owns

  • Time-linked evidence and event context
  • Timeline construction and reconstruction support
  • Cross-system memory and evidence relationships

Does not own

  • Semantic truth or policy interpretation
  • Governed execution
  • Completeness beyond the evidence actually linked

Receives

  • Lineage-bearing source material
  • Time-indexed events and evidence references

Produces

  • Reconstructed decision context
  • Explicit reconstruction boundaries

Stage 03

Governed run — Allagma

mechanical

Coordinates a bounded run over external runtimes while recording its operations and gates.

Owns

  • Run lifecycle and consequential-action custody
  • Explicit execution gates and event evidence
  • Replay coordination over recorded operations

Does not own

  • Provider or model-routing authority
  • Semantic or policy authority
  • Promotion authority

Receives

  • Reconstructed decision context
  • Declared run contract and gate requirements

Produces

  • Governed operation record
  • Run events and gate evidence

Stage 04

Controlled model access — Conexus

advisory · mechanical

Mediates access to model providers while preserving a bounded invocation record.

Owns

  • Provider and model routing
  • Model-call, usage, and cost evidence
  • The model-access boundary

Does not own

  • Semantic truth
  • Policy judgment
  • Promotion or legal authority

Receives

  • Governed model request
  • Routing and access constraints

Produces

  • Bounded model result
  • Model-call and usage evidence

Stage 05

Semantic and policy judgment — Kanon

semantic_authority

Applies named semantic and policy authority to a bounded result.

Owns

  • Canonical facts, ontologies, and semantic plans
  • Policy judgment and cited authority
  • Human semantic gates and decision records

Does not own

  • External execution
  • Model-provider routing
  • Final promotion or legal determination

Receives

  • Bounded model result and call record
  • Applicable facts, policy, and semantic context

Produces

  • Judgment with cited authority
  • Semantic decision record

Stage 06

Promotion and officialization — ARG

promotion_authority

Decides whether a result may cross a defined officialization boundary.

Owns

  • Promotion and officialization gates
  • Evidence and authority presence checks at the boundary
  • Fail-closed hold or denial behavior

Does not own

  • Semantic truth
  • Underlying model or runtime execution
  • Legal or regulatory compliance determinations

Receives

  • Judgment with cited authority
  • Required evidence and promotion policy

Produces

  • Promoted, denied, or held decision
  • Promotion-boundary evidence

Stage 07

Dossier and verification — ALL

evidence_authority · integrity_verification

Assembles and validates the bounded evidence record used for inspection, export, and integrity checking.

Owns

  • Dossier validation and evidence attachment
  • Evidence export and offline-verification boundary
  • Signature or integrity-metadata handling only when real approved material exists

Does not own

  • Semantic truth
  • Legal conclusions
  • Claims beyond the evidence attached to a dossier

Receives

  • Promoted, denied, or held decision
  • Linked run, authority, and promotion evidence

Produces

  • Inspectable dossier boundary
  • Publication-safe export only after approval

Stage 08

Replay and offline verification

integrity verification

Closes the loop by making an approved record replayable and independently inspectable when evidence is published.

Owns

  • Static replay, transcript, and offline-verification explanation

Does not own

  • The historical record
  • Correctness beyond the published evidence set
  • A legal or regulatory conclusion

Receives

  • Approved dossier evidence

Produces

  • Review findings returned to the governed loop

Responsibility transfers

What each stage receives and hands on

Functional labels appear before component names. The eighth stage closes the loop through replay and offline verification.

The topology explorer above is the primary system explanation. Every selection has an equivalent structured row and a complete responsibility panel that remains readable without JavaScript.

Cross-cutting lanes

Support without obscuring the main loop

Shared mechanics — Ontogony.Platform
Cross-cutting mechanics used by the governed loop.
Evidence canonization — Flock
A supporting lane for multi-agent evidence handling.
Redacted evidence intake — Vendor adapters
A boundary lane for vendor and runtime evidence.
Deterministic test range — Synthetic Estate
A controlled test lane outside the core decision sequence.
Operator and buyer projection — Workbench
A projection surface, not a source of truth.
Inspect replay anatomy View system status