Private AI
Ask over confidential data — with the model your security team will approve.
Public chatbots send prompts to someone else’s cloud. Private AI on Diode is the opposite: you plug self-hosted or partner-hosted models into Diode Nexus (product brand: Protected AI), then wrap them in an organizationally aware package — tools, channels, ranking, and Diode’s end-to-end encrypted path. Nexus tunnels into your private model so it is never exposed to the public Internet.
The pitch is not “pick another SaaS LLM.” It is: bring the inference your policy allows, then ground it in your systems.
Private AI models — self-hosted or partner-hosted Private AI, tunneled over Diode so the model is never on the public Internet:
Public LLMs — built-in OpenAI, Anthropic, xAI, OpenRouter, and Perplexity, routed under the same policy:
What this means
- Models you configure — Any private endpoint (Ollama, vLLM, or a partner-hosted OpenAI-compatible API). Nexus also has built-in support for OpenAI, Anthropic, xAI, OpenRouter, and Perplexity. You configure how private and public models are routed.
- Organization-aware tooling — MCP and tools so answers come from your registries, APIs, and files — not training cut-off alone.
- Protected agentic chat — Natural-language conversations with pipeline visibility while tools run.
- Traffic on Diode — Prefer Perimeter Discover or Diode binds so model and tool hops stay on your ZTNA / private path — not a naked public API call.
- Meet people where they work — Same package answers Diode Collab channels, web embeds, ACP for apps (including Vibe), and an OpenAI-compatible API (alpha).
Advantages
- No requirement to put confidential prompts on a multi-tenant public chatbot
- Security and compliance choose the model; operators still get a real chat + tool product
- One Nexus tenant serves Collab, Vibe coding, and custom apps — instead of every team wiring its own LLM
- Pipeline and tool activity is visible to operators, not a black box
- Works with existing Diode identities, zones, and perimeters
Applications
- Internal Q&A over policies, procedures, and operational data
- Supplier and extended-team questions answered inside a Collab zone
- Organization-aware coding and generation from Diode Vibe
- Plant / region inference that must stay on approved GPU or partner-hosted Private AI
- Embeddable help on private or protected Diode sites
- Agent APIs (ACP) so other apps call your Protected AI instead of inventing their own