P&L savings for your credit and market risk operations.
Determistic Modern Risk Platform. AI Orchestration.
Built on Google Cloud.
What is RaaS?
Results, not engine runs
Consume governed risk states—credit, market, capital, stress, and day-on-day explanations—with schemas, tolerances, and lineage baked in. The deterministic kernel stays fixed; AI orchestrates mapping and explanation only.
- Point-in-time batches, hard to reproduce
- Opaque lineage and QA burden
- Expensive integration per desk
- Schemas + tolerances + lineage badges
- Deterministic core with XVA, sensitivities, stress, SIMM/DIMM, SA-CCR/SA-CVA/FRTB-SA
- Consumption via API, BigQuery, PDF, console
Results contract
Five guaranteed outputs
Deterministic vs AI
Governed AI copilot with a deterministic boundary
AI orchestrates mapping, supervision, and explanations. Pricing, Greeks, XVA, stress, SIMM/DIMM, SA-CCR/SA-CVA/FRTB-SA remain deterministic and versioned.
- Data mapping, enrichment, clustering
- Movement explanations & narratives
- Policy alignment + Basel paragraph mapping
- Workflow assistance and QA suggestions
- Price or change the deterministic kernel
- Alter schemas, tolerances, or lineage
- Move beyond approved data domains
- Bypass governance and audit policy
Join the roadmap poll to steer allowed vs. not allowed AI features.
Results Contract
Schema-backed, regulator-ready outputs
Every result is versioned, tolerance-checked, and lineage-stamped. Confidence badges, Basel paragraph mapping, and deterministic kernels make regulators comfortable.
Result schemas
Structured JSON + PDF packs ready for API, BigQuery, dashboard, and regulator submissions.
Guarantees
- Schema + tolerance versions with SLOs
- Lineage + movement attribution per result
- Confidence and governance badges
- Regulator-ready narratives and Basel mapping
Access
- Managed SaaS on Google Cloud (APIs, BigQuery, Gemini, IAM)
- Self-hosted / managed deployment toggle
- Console, reports/PDF, API clients, dashboards
See the results stream in action
Deliver governed risk results, not just runs
Vannarho provides continuous, deterministic risk states with AI orchestration for explanations and mapping. Subscribe to results contracts with tolerances, lineage, and regulator-ready narratives.
- Deterministic kernel: curves, pricing, dividend, XVA explain, sensitivities, stress, SIMM/DIMM, SA-CCR/SA-CVA/FRTB-SA
- AI only supervises mapping, QA, and narratives—never pricing
- Deliver via API, console, BigQuery, or regulator-ready PDF packs
Commercial
Outcome-based, open-core + SaaS
Pay for governed risk results with lineage and SLOs. Keep core access for exploration; add validation services when you need benchmarked proof.
Test Core Engine
Python wheels for teams exploring the deterministic kernel and APIs before subscribing to results.
- Access APIs + SDKs
- Local development & tolerance tests
- Community + docs support
Integration, Validation & Benchmarking
Independent validation runs, benchmarking, and regulator-ready packs to prove the contract. We work alongside your teams to design future-state flows and set up the platform.
- Validation & benchmarking runs
- Capital & Basel mapping evidence
- Regulatory compliance advisory
- Cost + ops take-out plans
Managed Results (RaaS)
Subscribe to governed risk states (schemas, tolerances, lineage) with delivery via API, BigQuery, PDF, and console.
- Deterministic kernel: pricing, Greeks, XVA explain, stress, SIMM/DIMM, SA-CCR/SA-CVA/FRTB-SA
- Confidence + lineage badges per result
- Delivery via API, console, BigQuery, PDF packs
- Outcome-based pricing aligned to consumption
Results Catalog
Deterministic coverage that feeds every result
Curves, pricing, dividends, XVA explain, sensitivities, stress, SIMM/DIMM, SA-CCR/SA-CVA/FRTB-SA power every risk state. Browse the governed scope and pull sample JSON/PDF.
Result Tiles
Every analytic as a governed result
Each analytic becomes a result tile with schema, tolerances, lineage, and delivery options. Mix and match for trading desks, treasury, and regulatory teams.
- Pricing and cashflows (NPV/PNL, dividend accruals)
- Sensitivity Analysis (FD & AAD/GPU)
- Stress / what-if impact
- Exposure simulation & XVA + explain
- Capital attribution & Basel mapping
- SIMM*
*SIMM license not provided with Vannarho.
Capital & Regulator Contract
Regulator-ready results with Basel mapping
Deterministic capital outputs with lineage, paragraph mapping, and desk governance. Show regulators the schema, not the engine.
Credit Risk: SA-CCR
SA-CCR exposures as governed results with schema, tolerance, and lineage.
Credit Risk: BA-CVA & SA-CVA
BA/SA-CVA results with Basel paragraph mapping and audit trail.
Market Risk: FRTB-SA (Simplified & SBM)
FRTB-SA (simplified + sensitivities) with sensitivities lineage and governance badges.
Desk Reporting & Governance
Desk mandates, P&L, lineage, and approval workflows as part of the results contract.
TradeScript: Custom product kernel inside the deterministic boundary
Define products that inherit schemas, tolerances, explainability, and lineage. Keep AI out of pricing; keep custom logic inside a governed kernel with the same results contract guarantees.
- Define custom products with flexible scripting logic that auto-inherits schemas.
- Seamlessly integrate new instruments into the deterministic kernel.
- Extend analytics or create new valuation methodologies with governance built-in.
Practical Applications & Benefits
Benchmarking & Prototyping
Accelerate your model development and ensure accuracy with Vannarho as your powerful benchmarking tool. Validate proprietary internal models against our robust analytics engine.
- Rapid validation of internal pricing and risk models.
- Inform primary model development without rebuilding core components.
- Focus on innovation by leveraging our established infrastructure for discount curve construction, risk factor evolution, and exposure simulations.
Independent Model Validation
Empower your Model Validation teams with an independent, transparent, and robust analytical framework.
- Save significant time and resources on "offline" model creation.
- Ensure thorough and efficient validation processes with a trusted external benchmark.
- Enhance regulatory confidence with clear, auditable validation results.
Core Pricing & Risk for Banks
Vannarho provides a sophisticated, primary pricing and risk model for institutions of all sizes.
- Ideal for smaller-to-medium-sized institutions lacking large vendor software budgets.
- Reduce reliance on extensive internal development teams for core functionality.
- Gain access to advanced risk management capabilities previously out of reach.
Operating Model Outcomes
Capital confidence and ops efficiency
Ops reduction
35%
Less reconciliation and QA through deterministic outputs.
What-if speed
4x
Faster scenario turnaround with reusable risk states.
Team size
-25%
Clear governance boundary reduces support burden.
Cost Reduction
Before/after stack & waterfall
Cost drivers
- Automation of recon/QA
- Deterministic outputs reduce rework
- AI explanations speed investigations
- Shared schemas lower integration effort
- Managed ops reduce infra & headcount
Before vs after
Comprehensive Documentation
Access the full Vannarho user guide for step-by-step instructions, reference details, and examples to get the most from the platform.
User Guide
Download the full guide and explore the key sections that accelerate setup and ongoing use.
Product & Analytic Scope
Data Flow
Building VRE
Parametrization
Examples
Developer Resources
Access our tools and repositories to seamlessly integrate Vannarho into your development workflows.
Built on Google Cloud
Vannarho leverages the power of Google Cloud to provide a scalable, secure, and intelligent SaaS platform for risk management. Prefer to self-host? Toggle to managed deployments without losing the contract.
API Gateway
Front door for ingestion, schema validation, and scheduling risk jobs; enforces tolerances and lineage headers on every request.
BigQuery
Landing zone for governed risk states, attribution, and sensitivities; power users query results contracts directly.
Gemini Enterprise
Drives narratives, lineage explanations, and AI copilot within the deterministic boundary—never pricing.
IAM & Security
IAM and Security Command Center harden access to results contracts, schemas, and operational tooling.
Kubernetes
GKE runs the deterministic kernel, GPU/AAD sensitivities, and scaling of pricing/XVA/state generation.
Logging & Monitoring
Centralized observability for risk runs, lineage events, tolerances, and delivery pipelines.
Cloud Functions
Event-driven glue for contact flows, feature polls, enrichment hooks, and delivery automation.
Pub/Sub
Messaging backbone for ingestion, QA events, orchestration triggers, and downstream delivery updates.
Redis / Memorystore
Low-latency cache for session state, poll counts, lineage lookups, and orchestration speed-ups.
Architecture
Portable stack: inputs → AI orchestration → deterministic kernel → results contract → delivery
Toggle cloud or self-hosted. AI handles mapping and explanations; the deterministic kernel produces versioned results contracts delivered via API, console, BigQuery, or PDF.
Ingestion & orchestration
Feeds, mapping, QA, clustering; AI assists but cannot change kernels.
Deterministic kernel
Curves, pricing, XVA explain, sensitivities, stress, SIMM/DIMM, SA-CCR/SA-CVA/FRTB-SA.
Delivery
API, BigQuery, console dashboards, regulator-ready PDFs; managed SaaS or self-hosted.
Delivery
Choose how you consume results
API
Schema-first APIs with lineage headers and tolerance checks. Perfect for embedding risk states.
- Python/REST clients
- Per-result provenance
Console
Web console for lineage, movements, and AI explanations. Great for CROs and desks.
- Result streams + schema badges
- Regulator-ready narratives
Reports / PDF
Regulator packs, audit narratives, and exec-ready summaries with mappings and tolerances.
- Basel paragraph references
- Movement explanations
Help Choose Our Next AI Breakthrough
We distilled the leading ideas from our AI research backlog. Cast your vote and tell us which innovation would elevate your risk practice the most.
What matters most?
Your feedback steers where we invest engineering time—from smarter explainability to faster onboarding and supervision tooling. We will share outcomes with the community.
- Vote once and immediately see how the community is prioritising features.
- Optionally add your own idea if we missed something critical.
- We only store aggregate counts publicly and anonymise free-text suggestions.
Live Results
Collecting community feedback...Loading poll data...
Book a demo and/or a validation run
See a demo with synthetic data. Then, when you are ready, get your results contract: risk states with schemas, tolerances, lineage, and regulator-ready narratives. We will run your data and share the outputs.
Schedule now