How ARBI works
An honest map of what exists today, what is illustrative, and what is planned. Transparency matters more to us than appearing finished.
ARBI today
ARBI currently exists as an Experience Edition. This release is focused on getting the executive experience right — validating the decision workflows, the boardroom workspaces, the trust framework, scenario evaluation, and the overall information architecture — before any enterprise data is connected.
It demonstrates exactly how ARBI is expected to operate. To make that experience real and testable, the datasets, relationships, recommendations and scenarios are illustrative — built on a synthetic reference enterprise so leaders can evaluate the decision experience before full backend integration. What you judge today is the experience and the method, not the numbers.
From data to outcomes
In plain terms, ARBI moves along one path — and every step stays connected to the one before it.
Start with what's happening in the business, gather the evidence behind it, turn that into insight, weigh the decision options, and steer toward a better outcome — with the reasoning visible the whole way.
Why you can trust what you see
Trust is built from four things. Here is the honest status of each.
| Element | Current status | Planned status |
|---|---|---|
| Source transparency | Sources and a source trail are shown for each topic — using illustrative data. | Live lineage back to the originating enterprise systems. |
| Evidence transparency | 20+ benchmarked indicators per hero topic, each visible and traceable (illustrative values). | The same indicators, measured from real data. |
| Confidence scoring | A real, deterministic reliability score (evidence quality, source coverage, framework support, freshness) — on illustrative inputs. | Identical method, computed on live evidence. |
| Explainability | Live today: the full chain and key assumptions are always visible. | Extended with AI-assisted plain-language explanation. |
The seven layers
Each layer rests on the one below it; data flows upward from the sources to the executive experience. Today, only the top layer is live.
Boardroom-ready decision workspaces — the part leaders actually use.
Decision workspaces, lenses, trust panels
Connected to live enterprise data
Help leaders explore, interpret and explain — never to decide for them.
LangGraph · RAG · LLM services
AI-assisted navigation and explanation, human-in-control
Turn evidence into recommendations, scenarios and reliability scores.
Python · business rules · simulation models
Operational, data-driven decision services
Connect workforce, capability, operational and business concepts.
Neo4j · knowledge-graph concepts
Contextual relationship intelligence
Shape raw data into clean, business-ready datasets.
dbt
Automated transformation + semantic business models
Centralized, analytical foundation that scales.
BigQuery
Enterprise-scale analytical data platform
The enterprise systems where workforce and business data lives.
HRIS · ATS · Learning · Workforce Planning · ERP · Operations · Labor-market
Connected enterprise datasets
BigQuery gives an enterprise-scale, analytical foundation that handles large workforce and operational datasets without heavy infrastructure. dbt turns that raw data into clean, well-defined, business-ready models — so every number has a consistent, documented definition feeding the layers above.
Workforce risk is rarely one number — a skills gap connects to attrition, to capacity, to a business outcome. A relationship layer (Neo4j) captures those connections so ARBI can reason about context, not just isolated metrics.
ARBI is not intended to replace decision-makers. When AI is added, it will support exploration, interpretation, explanation and scenario understanding — helping leaders grasp the evidence faster. Human leaders remain responsible for the decisions. The reasoning will stay visible and inspectable, never a black box.
What's real today, what's coming
| Capability | Current Experience Edition | Future production platform |
|---|---|---|
| Data sources | Illustrative reference dataset (a synthetic enterprise) | Connected live enterprise systems |
| Recommendations | Curated and rule-based, designed to validate the experience | Generated from live data and analytics models |
| Scenarios | Deterministic, pre-modelled trade-offs | Data-driven scenarios on real baselines |
| Benchmarks | Illustrative PY / target / industry / best-in-class | Sourced from real internal history and market data |
| Confidence (reliability) scores | Real deterministic method, illustrative inputs | Same method applied to live evidence |
| AI assistance | Not yet — interactions are structured, not generative | AI-assisted exploration and explanation |
| Decision workspaces | Implemented and usable today | Unchanged experience, powered by live data |
| Trust framework | Live: source trail, evidence, assumptions, reliability | Extended with real system lineage |
From experience to enterprise
Six phases. We are at Phase 1.
Validate the executive experience, decision flow and trust model.
Boardroom workspaces, lenses, scenarios, trust framework.
Proves the experience and aligns stakeholders before any data cost.
Stand up the analytical platform and business-ready datasets.
Central data platform; transformed, modelled datasets.
A scalable, trusted single source for everything above it.
Connect workforce, capability, operational and business concepts.
Relationship layer linking the objects ARBI reasons over.
Context-aware insight instead of isolated metrics.
Make recommendations, scenarios and reliability data-driven.
Operational decision services replacing curated content.
Recommendations grounded in the enterprise's own data.
Assist exploration, interpretation and explanation.
AI-assisted navigation and plain-language explanation.
Faster understanding — with humans still deciding.
Run on live enterprise data inside real decision workflows.
Connected, governed, production deployment.
ARBI becomes a durable layer of how the enterprise decides.
Straight answers
No. The current Experience Edition runs on an illustrative reference dataset — a synthetic enterprise designed to validate the decision experience. Connecting live data is Phase 6.
No. BigQuery is the planned data platform (Phase 2). It is not yet part of the running product.
No. dbt is the planned transformation layer (Phase 2). It is not yet running.
No. The relationship layer is a conceptual design today (Phase 3).
No. Today's interactions are structured, not generative. AI assistance (Phase 5) is planned, and even then it will assist exploration and explanation — it will not make decisions.
No. Recommendations are currently curated and rule-based to validate the experience. They become data-driven in Phase 4.
The datasets, evidence values, benchmarks, recommendations and scenarios are illustrative. The reliability scoring method, the decision workflow, the lenses and the trust framework are real.
A live data platform (BigQuery/dbt), a relationship layer (Neo4j), data-driven decision intelligence (Python/analytics/simulation), AI assistance (LangGraph/RAG/LLM), and enterprise deployment.
It is trustworthy as a faithful demonstration of how ARBI is designed to operate — and it is honest about its data. Every figure is labelled illustrative; nothing here should be read as a measurement of a real company yet.
Our principle: transparency over hype. If something here isn't built yet, we say so. What you can rely on today is the experience, the decision method, and the trust framework — and a clear, honest plan for everything else.