What is the AI Assistant?
The AI Assistant in Cordatus is a conversational control layer over the entire platform. Cameras, devices, recordings, AI jobs, alarms, and streams — everything you do in the Cordatus dashboard can now be done in plain language. Instead of hunting through menus, you simply describe what you want, and the assistant turns your intent into real, permission-scoped platform actions.
It sits on top of the platform you already trust — it does not replace it. Every action the assistant performs is the same action available in the dashboard, executed through the same permission-scoped APIs, so results are always real, scoped, and auditable.
Why the AI Assistant?
Unlike a generic chatbot that only answers questions, the Cordatus AI Assistant executes real operations across the platform:
- Natural language: No commands or syntax to memorize — describe what you need in your own words.
- Real actions: Calls the same permission-scoped platform APIs used by the dashboard. Every action is real and auditable.
- Permission-scoped: The assistant can only do what your account is allowed to do — it inherits your exact roles and permissions.
- Multilingual: Understands and replies in your language.
- Card-based interaction: When a request is ambiguous, the assistant shows selection cards (cameras, devices), confirmation cards, and summaries instead of guessing.
- Context-aware: Multi-turn flows (for example, "create a calendar" → "confirm") keep their context so follow-up messages land in the right place.
Who is it for?
Operators:
- No menu-hunting — describe what you need and the platform does it.
- Fast, everyday actions like opening a camera, starting a recording, or checking a device.
Engineers & Administrators:
- The assistant calls the same permission-scoped platform APIs you already use — every action is real, scoped, and auditable.
- Manage cameras, devices, jobs, alarms, and schedules without leaving the conversation.
Multi-site teams:
- Control streams, recordings, and AI jobs across sites from a single conversational interface.
Core Capabilities
| Domain | What you can do |
|---|---|
| Camera & Stream Control | List cameras, open and close live streams, manage camera layouts and templates |
| Recording Control | Start, stop, schedule, and review recordings |
| AI Job Control | Launch and stop inference jobs — the assistant picks the right model for your goal |
| Alarm Management | Create, list, and review inference and device alarms |
| Device Operations | Connect to edge devices and check live CPU / GPU / memory / status |
| Scheduling & Calendar | Recurring calendars that run jobs, recordings, and alarms on time via Cossa |
Key Concepts
- AI Assistant — The conversational interface that turns natural language into real platform actions.
- Intent — What you want to happen, expressed in your own words.
- Action / Command — The real platform operation the assistant performs on your behalf (e.g., opening a stream, starting a recording).
- Selection card — An interactive card shown when a request needs clarification (e.g., which camera or device).
- Confirmation — For sensitive or irreversible operations, the assistant asks you to confirm before acting.
- Permission scope — The set of roles and permissions on your account that bound everything the assistant can do.
- Cossa — The Cordatus Smart Scheduling Agent that executes scheduled jobs, recordings, and alarms.
How it works
- You describe what you want in plain language (any supported language).
- The assistant understands your intent and routes it to the right domain (cameras, recordings, jobs, alarms, devices, or scheduling).
- If anything is ambiguous, it asks with a card (which camera? which device?) instead of guessing.
- For sensitive actions, it asks for confirmation.
- It performs the real action through the same permission-scoped APIs as the dashboard.
- You see the result — a live stream, a started recording, a running job, or a summary card.
New to the assistant? Start with the Quickstart to run your first command in a couple of minutes.