AI Cockpit

AI Cockpit

The AI Cockpit is the operator's surface for tuning the AI that runs across the app — guest reply suggestions, Pulse Copilot, task-template assistance, message analysis, accounting agents.

Open it from the V28 sidebar → AI Cockpit.

AI Cockpit Overview — system health, 7-day spend, active prompts, validators, failed calls

Sections

  • Agent catalog — what the AI does, named. The inventory of every autonomous capability across the four families — chat specialists, validators, event agents, background agents — with each one's trigger, autonomy, and where its toggle lives. Start here if you are asking "what can the AI do?".
  • Agents editor — per-specialist (accounting / messaging / operations / knowledge / property / marketing — the Listing Advisor / general) prompt + model + thinking-budget + tool-rounds + plan-then-execute. These are the catalog's Family 1 specialists.
  • Prompts editor — the existing llm_prompts editor for the named slugs (message_analysis, wa_chat_assistant, etc.).
  • Cost dashboard — per-turn drill-down of accounting agent and Pulse Copilot runs.

The Validators tab configures the catalog's Family 2 guards (incl. the Outbound Guard); the Event Agents tab configures Family 3 (the maintenance agent). The always-on background agents — Stay Planner, Readiness Checker, Mood Watch, Knowledge Keeper, Price Scout — are controlled from the surfaces named in their catalog entries.

What lives here vs Admin → LLM Prompts

The legacy Admin → LLM Prompts page (covered separately in admin/llm-prompts.md) edits the same llm_prompts table. The AI Cockpit Prompts tab is the V28-native version of that surface; the legacy page is still available and still works.

Going forward, all per-tenant AI configuration is being moved into the AI Cockpit.

Per-tenant from day one

Everything in the AI Cockpit is scoped to your tenant. Editing the accounting agent's system prompt in flatsbratislava does not change the accounting agent for another tenant. Each tenant tunes their own agents.

All edits go through an audit log — see who changed an agent's model or prompt and when, via Admin → Audit Log (see admin/activity-log.md).

Source: the luxury.host operator manual.