Live demo scenarios5 reproducible security proofs: No provider API keys in agent pods • gVisor Python sandbox • Cryptographic tenant isolation • Gateway request circuit breakerExplore the 5 Proofs
Solutions · Financial Services & Banking

Run research and advisory agents under strict egress, key custody, and audit controls.

Deploy LangGraph, LangChain, and Deep Agents workloads on Kubernetes with zero model keys in agent pods, gVisor isolation for quantitative Python scripts, read-only tenant-scoped Postgres queries, and self-hosted Langfuse traces.

Risks

Where it fails without a runtime boundary

Exposed Model API Keys

Putting OpenAI or Bedrock credentials in agent pods risks key theft during a prompt injection. How Zelkor stops it: Provider keys stay in gateway Kubernetes Secrets; agent pods hold only a local gateway token.

Unsafe Quantitative Python Execution

Running generated portfolio math inside the agent container exposes the pod’s filesystem and service account. How Zelkor stops it: Untrusted Python runs over MCP in a warm pool of gVisor worker pods.

Cross-Desk Data Leakage

Shared research graphs queried by multiple desks risk returning another client’s holdings. How Zelkor stops it: Verified JWT identity sets the tenant session for Postgres Row-Level Security and forces tenant filters on Qdrant.

Destructive Database Queries

Hallucinated SQL statements attempting to modify or delete core financial records. How Zelkor stops it: The Postgres MCP tool enforces read-only queries.

Runaway Model Loops

Recursive agent loops firing hundreds of model calls per minute. How Zelkor stops it: The AI gateway enforces a per-minute request cap and rejects extra calls before reaching the provider.

Client Prompts in Cluster Logs

Standard container logs capturing sensitive account numbers and prompts. How Zelkor stops it: Default log settings omit prompt bodies, bearer tokens, and API keys.

Controls

Compliance & Control Mapping

RequirementWhat Zelkor DoesHow You Check It
Network Segmentation (DORA / PCI-DSS)Kubernetes NetworkPolicy blocks agent pods from calling the internet, sandbox workers, or databases directly.Run The Vanishing Key and The Shell Moved network proofs.
Credential Custody & Access (SOC 2)Keeps upstream LLM keys on the gateway and rejects unsigned or invalid JWTs at the front door.Inspect pod environment variables and run negative JWT tests.
Multi-Desk Information BarriersPropagates verified user identity to MCP tools, sets Postgres tenant sessions for RLS, and filters Qdrant by tenant.Run Two Desks, One Graph cross-tenant proof.
Model Risk Audit Trail (SR 11-7)Records full run waterfalls and automated run checks in self-hosted Langfuse; inspects prompts with NeMo Guardrails.Review run traces in Langfuse via The Flight Recorder proof.
Topologies

3 Financial Services Workflows

Multi-Desk Institutional Research

Serve equity and credit research across separate desks from one LangGraph deployment while enforcing desk-level isolation in Postgres and Qdrant.

Sandboxed Quantitative Backtesting

Execute agent-written Python valuation models inside the warm gVisor worker pool with no access to the agent pod or external networks.

Guardrailed Client Advisory Copilot

Route every chat completion through fail-closed NVIDIA NeMo Guardrails for topic safety and cap request rates at the cluster gateway.

Deploy auditable financial agents inside your own Kubernetes cluster.