AI Providers ​

An AI provider is a connection InfraScout uses to talk to a Claude model. The Providers tab is where you register the API keys, choose the default model, and set the per-tenant memory rollup behavior. End users pick which provider drives a conversation from the Chat launcher; they cannot configure new providers.

AI Providers tab with three Claude connections (ITdesign Anthropic Haiku, ITdesign Anthropic Opus, ITdesign Anthropic Sonnet) showing model, max tokens, API key, default flag, and memory rollup

Layout ​

The page header carries the AI Integrations title and the Admin Access chip; the tab strip puts you on AI Providers. Two header buttons sit above the connection grid: Add Connection and Refresh. A search box filters by provider name.

The body is a card grid — one card per registered provider. The total count (N of N connections) is in the top-right corner.

Card contents ​

Each provider card carries the connection metadata:

  • Connection name — a human-readable label ("ITdesign Anthropic Haiku").
  • Vendor chip — Anthropic today.
  • Model — the exact Claude model string (Claude Haiku 4.5, Claude Opus 4.7, Claude Sonnet 4.6, etc.).
  • Max Tokens — the per-response token budget. Defaults map to the model's max output.
  • API Key — masked, with the last few characters shown for identification.
  • Default — a checkmark when this provider is the tenant's fallback; blank otherwise.
  • Memory Rollup — whether this provider is allowed to rewrite memory entries on each turn (Custom or blank).

The action row: Test connection, Edit, Delete.

What "default" means ​

Exactly one provider per tenant is marked Default. The default is what the Chat launcher preselects in the AI Provider dropdown. End users can choose a different provider for a single chat, but the default decides what happens when they do not choose at all.

Switching the default is a one-click operation from the Edit dialog: tick the Default box on the new provider and the previous default is unmarked automatically.

Memory rollup ​

The Memory Rollup field decides whether the provider is allowed to summarize and rewrite the persistent Memory entries between turns. Custom uses a tenant-specific rollup prompt; an empty value means the model can read memory but cannot rewrite it. We recommend enabling rollup on at least one provider — typically the cheapest one — so memory stays compact across long sessions.

Common workflows ​

Most tenants register three providers — a fast/cheap model for inventory queries and short answers, a balanced mid-tier model for standard assessments, and a top-tier model for the trickiest investigations — and let users pick at chat start. Rotating an API key is a single edit on the existing card; the in-flight chats continue against the cached connection until they finish.