Security
Epic AI's security model is a structural guarantee enforced within the SDK runtime — not a promise written in a policy document. Credentials, raw data, and tool schemas never cross a network boundary unless you explicitly authorize it.
Data Sovereignty
MCP tool schemas are resolved and cached on-premise inside the SDK runtime. The orchestration layer never transmits schema definitions to an external service.
API keys, tokens, and connection strings are injected at runtime via environment variables or your secret store. They are never serialized into prompts or sent to the language model.
Tool outputs — query results, file contents, system state — are processed locally by the SLM. Only the derived response leaves the boundary, and only when you direct it.
The SDK is designed to operate with no outbound internet access. The local SLM inference path, adapter registry, and audit store function entirely within your network perimeter.
Tiered Autonomy
Read-only queries, status checks, and informational lookups execute immediately. No human in the loop. Latency equals inference latency.
Write operations and state changes are executed and simultaneously surfaced to the designated escalation channel. Full audit entry is written before the action completes.
Destructive, financial, or cross-system actions are blocked at the adapter boundary. Execution waits for explicit human approval via webhook, Slack, or the Praetor console.
Audit
Every tool invocation, tier decision, approval event, and model response is written to an append-only audit log with a cryptographic chain. Each entry contains a hash of the previous entry, making retroactive modification detectable without a separate integrity service.
Logs are written before the action executes — not after — ensuring that a crash or network partition never produces an action without a record.
Vulnerability Disclosure
We operate a responsible disclosure program. If you discover a security vulnerability in Epic AI's SDK, platform, or infrastructure, please report it privately before disclosure. We acknowledge all reports within 48 hours.
security@epic-ai.io