Skip to main content

Flagship Projects

Three production-grade AI systems — each designed to publish six benchmark numbers and run on real infrastructure.

#ProjectDomainInfraKey differentiator
P1Enterprise Knowledge PlatformAny / cloudManaged cloud10k+ docs, hybrid RAG, eval CI, full observability
P2Workflow Automation PlatformBusiness workflowsCloud / hybridMCP servers, agent orchestration, human-in-the-loop, reliability SLOs
P3Insurance Compliance CopilotRegulated / sovereignminicloud k8sAI Act compliance, PII pipeline, self-hosted models, Cosign, audit lineage

The six benchmark numbers

Every project publishes these with methodology:

  1. Groundedness rate (%)
  2. Citation accuracy (%)
  3. Refusal rate on out-of-scope (%)
  4. p50 / p95 / p99 latency (ms)
  5. Cost per resolved query (€)
  6. Hallucination rate on adversarial set (%)

Progression logic

P1 → P2 → P3 is a deliberate ladder. P3 requires everything from P1 and P2, plus compliance-governance and full AI Act controls. Do not skip.