SentinelAI

Deployment Modes

Blocking, monitoring, async, and self-hosted — pick your risk posture

Deployment Modes

SentinelAI adapts to your risk posture and throughput.

The four modes

ModeUse caseBehavior
BlockingCustomer-facing chat, copilotsVerify every response before it hits your user; serve, correct, or block
MonitoringEvaluation, staging, low-risk featuresLog everything, review flagged ones later
AsyncHigh-throughput pipelinesFire-and-forget analysis with webhook callbacks
Self-hostedRegulated industries, data residencyEverything runs on your own infrastructure

Blocking

The default. Your app sends the prompt/response pair, SentinelAI returns the verdict, and your app acts on it — all before the user sees anything.

result = client.verify(prompt=prompt, response=llm_output)

if result["status"] == "hallucinated":
    return result["corrected"]  # serve the fix, not the flaw

Monitoring

Log everything, act later. Perfect for post-hoc analysis, drift detection, and compliance auditing without adding latency to the request path.

Async

For high-throughput workloads where you can't wait for a verdict inline:

  • Fire-and-forget the analysis
  • Receive the result via webhook
  • Store and aggregate at your own pace

Self-hosted

The open-source core runs entirely on your infrastructure. Data never leaves your network. The same SDK, the same detectors, the same API — just your hardware.

Self-hosting is free and open source. The managed cloud adds dashboards, alerting, and settings management on top of the same core.

On this page