AI Pilot deployment modes

Audience: Platform engineers, AI governance architects
Time: ~12 min read

AI Pilot runs on the same universal bouncer binary. For AI governance, choose Gateway Mode or App-Embedded — enterprise labels for where the PEP sits on the path. Broader topology (including Shadow) is covered in Deployment modes.

What

ModeEnterprise labelPlacement idea
Shared edge hopGateway ModeClients and apps send AI traffic to a shared bouncer VIP/DNS; the bouncer forwards to LLM/GenAI upstreams.
Co-located with the appApp-EmbeddedBouncer runs next to one application; that app’s AI egress goes through the local bouncer.

Both modes use the AI Inspection Engine for PII and safety, and the same controls from the Control Plane.

Why

  • Gateway Mode — centralize governance for many apps and providers with one (or few) PEPs; simpler DNS cutover for LLM base URLs.
  • App-Embedded — lowest hop latency per app, strong isolation per workload, natural fit for Kubernetes pods.

How — capability matrix

ConcernGateway ModeApp-Embedded
TLS terminationOften terminates client TLS at the bouncer (or LB in front); upstream TLS to providers as configuredUsually localhost/mesh to the app; egress TLS to providers from the bouncer
DNS / routingPoint LLM base URLs or edge DNS at the bouncerApp config points at local bouncer listen address
PlacementShared network hop in front of many workloadsSame host/pod as one workload
Redis (token limits)Strongly recommended for shared global counters across replicasRecommended if you scale multiple replicas of the same embedded pattern
Blast radiusMisconfig can affect all apps behind that VIPLimited to the co-located app
When to useEnterprise AI edge, multi-app LLM gateway, shared MCP brokerPer-service AI governance, strict tenancy isolation, mesh-style pods

Technical reference (env names only)

Enterprise labelTypical BOUNCER_TYPETypical TARGET_HOST
Gateway Modereverse-proxyShared upstream (API gateway, LLM router, or provider-facing proxy)
App-EmbeddedsidecarLocal application listen address

Full install steps: Quick start · platform Deployment modes.

Verify

  1. In AI Pilot, select the bouncer — badge shows Gateway Mode or App-Embedded.
  2. Send traffic only via the intended path; confirm Activity rows.
  3. Attempt a direct provider call (bypass) — it must not appear in AI Pilot (proves governance coverage).

Troubleshooting: Badge and docs disagree? The badge reflects how that PEP was registered/deployed. Redeploy with the correct type; see Troubleshooting — By deployment mode.

Troubleshoot

SymptomGateway Mode tipApp-Embedded tip
502 / upstream errorsCheck shared TARGET_HOST and provider reachability from the bouncer networkCheck local app still listening; confirm loopback target
Some apps ungovernedThose apps still call the provider DNS directlyOnly the co-located app is in scope — deploy another embedded bouncer or move to Gateway
Token limits driftAdd Redis for the gateway replica setAdd Redis if multiple replicas share the same logical limit

Next steps