Skip to main content

Runtime Services

Siesta AI uses independently deployable services so that public ingress, platform APIs, retrieval workloads, external tools, and background processing can be secured and scaled separately.

Workload Groups

WorkloadPurposeOperational focus
FrontendUser and embedded interfacesTLS, origin policy, health, user-facing availability
Platform APIAuthentication, entities, agents, workflows, business logicAuthorization, database health, latency, audit correlation
Retrieval APIQuery-time retrieval and search operationsPrivate access, search latency, model and index dependencies
Retrieval workerIngestion, extraction, chunking, embeddings, indexingQueue depth, retries, poison items, throughput, quota
Tool serviceGoverned calls to external systemsCredential scope, approval, provider failures, egress
Function and scheduled workloadsEvent-driven and background processingIdentity, idempotency, retries, timeout, dead-letter handling

Production Requirements

Every workload should have:

  • a dedicated runtime identity where practical,
  • explicit inbound and outbound network paths,
  • minimum and maximum scale appropriate to the workload,
  • startup and health probes,
  • bounded retries and timeouts,
  • structured logs, metrics, traces, and correlation IDs,
  • documented dependencies and failure behavior,
  • a rollback or recovery path.

Avoid embedding secrets directly into runtime environment values. Reference a secret store or fetch secrets through the workload identity. Separate static configuration from secret-classified values as described in Secrets and Configuration.