Skip to content

On-Premises LLM Deployment

Description

Supports deployment of open-weight large language models on customer-controlled infrastructure, enabling AI conversation capabilities with full data sovereignty. The platform manages model serving, versioning, and integration with the conversation orchestration layer.

Canonical use case

A defence contractor deploys an air-gapped LLM instance to power its internal helpdesk bot, ensuring no conversation data leaves the secure facility network.

Open Items

  • [ ] Canon alignment — populate canon_axiom_refs or confirm no existing axiom applies
  • [ ] Dependency assessment — set dependencies_assessed: true once SA has reviewed the full chain
  • [ ] effort_estimate — replace 0 with rough engineering days (order of magnitude)
  • [ ] public_description — write the public-facing description before publishing