Phase 1 - Immediate FP&A foundation

Driver Ontology Manager

Create the semantic model that converts operational drivers into financial outcomes for driver-based FP&A.

Business problem: Planning systems store forecast numbers, but the target model requires the business to supply operational drivers that FP&A converts into revenue, margin, cash, EBITDA, FCF, and ROACE outcomes. Open JSON contract Back to foundations
Runtime Hardening Proof

Execution evidence from Enterprise Decision Runtime service

This panel is generated from runtime service functions on each request: event correlation, policy simulation, learning metrics, agent guardrails, decision trace, and audit package export. It closes the view-vs-system gap by showing the platform executing, not only describing architecture.

7registered agents
5registered policies
1correlated signal(s) from 3 events
$450.0Kpolicy simulation amount
100.0%human acceptance over 2785610 decided executions (90d)
5825088decision memory records
BLOCKbad-data guardrail result
route_to_human_supervisoragent failure fallback
Live event correlation
SignalPriorityImpactEvent IDs
sig-2efe089ec8P1$1.4Mevt-001, evt-002, evt-003
Policy + guardrail hardening
ControlRuntime value
Policyhuman-approval-policy
Prior threshold$50.0K
Simulated threshold$100.0K
Outcomeescalate
Approval volume change-18%
Guardrail failuresmissing_evidence, low_source_confidence, writeback_requires_human_approval
Hallucination guardevidence_required_before_recommendation
Replay + audit export
ArtifactValue
Audit packageaudit-97ab17991395
Integrity hashc80fd1aea51cec3d76a8d2e6346938acd1938531f544f8f3f7fd3917f1d6c98c
Regulatory export readyTrue
Trace steps10
Runtime chainSignal -> Context -> Ontology -> Policy -> Evidence -> Decision -> Governance -> Action -> Replay -> Learning
Runtime APIs
Endpoint
/api/finance-foundations/runtime-proof
/api/finance-foundations/driver-ontology-manager/runtime-proof
/api/iaf/enterprise-decision-runtime/learning-metrics
/api/iaf/enterprise-decision-runtime/agent-guardrails
/api/iaf/enterprise-decision-runtime/policy-simulation
/api/iaf/enterprise-decision-runtime/event-correlation
Hardening stance: agents fail closed to human supervision on missing evidence, low source confidence, or write-back attempts. Learning is measured, replay-backed, and cannot change policy or autonomy without approval.
Open Enterprise Decision Runtime Open runtime proof JSON
North Star runtime outcome

Operational drivers become first-class governed objects linked to financial outcomes, policies, evidence, scenarios, and forecast actions.

Core components
ComponentCapability
Production DriversOil production, gas production, LNG throughput, refinery utilization, maintenance hours, and outage windows.
Commercial DriversVolume, price, margin, customer/channel mix, trading volume, contract terms, and commodity exposure.
Corporate DriversHeadcount, contractors, projects, capex releases, AUC status, and discretionary spend.
Driver Relationship GraphMaps driver -> financial outcome -> KPI -> forecast -> policy -> evidence -> owner.
Driver Explorer UIShows driver dependencies, forecast impact, risk impact, source freshness, confidence, and scenario sensitivity.
Success metrics
MetricTarget
Driver coverage90% target
Outcome mapping95% target
Driver freshnessDaily target
Scenario sensitivity<5s target
FP&A deck alignment
Target operating-model theme
Driver-Based FP&A
Business supplies operational drivers
Centre converts drivers to financial outcomes
Forecast impact
Agent family
AgentPurpose
Driver Discovery AgentFinds candidate operational drivers and missing driver coverage.
Driver Mapping AgentMaps operational drivers to financial outcomes and forecast accounts.
Driver Sensitivity AgentQuantifies forecast and cash sensitivity to driver movement.
Proof links
SurfaceRoute
FP&A Decision OSOpen
FP&A Command CenterOpen
Context GraphOpen
Ontology ExplorerOpen
API contract
Endpoint
/api/finance-foundations/driver-ontology-manager
/ui/fpa-decision-os
/ui/fpa-command-center
Validation questions
Question
Which operational driver changed?
Which financial outcomes does it affect?
Who owns the driver and source data?
Can the driver-to-forecast chain be replayed?