The AI Assistant

Ordinary Animator includes an AI Assistant that can answer questions about your production, navigate to any entity, retrieve data, and help with production tasks. You talk to it by voice or text. There is just one Assistant -- behind the scenes it draws on configurable agents (see Configuring agents below), but you never have to pick between them.

One of the most useful everyday moments is field help: when a property asks for something and you're not sure what, the Assistant explains what belongs there and offers to draft it.

What the Assistant can do

The Assistant has a set of tools it can call:

• Navigation -- open any page (project, episode, scene, shot, character, location, prop) by name or ID
• Entity queries -- list all characters, find a location by description, retrieve a shot's details
• Data retrieval -- read screenplay text, look up voice settings, check what media a shot has
• UI commands -- trigger actions on the current page

The Assistant is stateless between sessions. It works from your saved project data and doesn't maintain memory across conversations.

Voice vs text

Voice -- The voice Assistant streams audio live. It uses built-in Voice Activity Detection (VAD) to detect when you're speaking and when you've finished. Responses stream back as audio. This is the primary interface for hands-free production work.

Text -- The text interface is a standard chat panel. Useful when you want to read long responses, copy text, or work in a quiet environment.

Both interfaces share the same logic and tools.

The voice streaming model

Voice is a live, two-way audio stream: you talk, the Assistant listens and responds in real time, with no push-to-talk. The Assistant is stateless -- it keeps no state of its own, so it can restart at any time without losing your project data.

Configuring agents

Behind the single Assistant sit one or more agents -- the specialists it draws on. Each project can have multiple agent configurations, each with:

• A name
• System instructions -- the role and context for this agent
• Context documents -- additional reference material the agent reads
• Tools -- which tool categories the agent can use

Agent configurations are managed in the project's Agents view. Default agents are seeded when a project is created. You can create specialised agents -- one focused on story continuity, one on technical production questions, etc. The Assistant draws on the right agent for you; you still talk to one Assistant.

Credits and usage limits

AI features (the Assistant, field help, speech generation) consume credits -- 1 credit is roughly one US cent of estimated AI cost. Your running total appears in the left navigation and the account menu.

Each account has a usage limit as a safety net against accidents (like a microphone left streaming). When you reach it, AI features pause and you'll see a message saying the limit was reached -- the rest of the app keeps working normally. Contact support to have your limit raised.

Using the Assistant effectively

The Assistant works best when your project data is complete and well-organised. It reads character profiles, location descriptions, shot details, and screenplay text to ground its answers. Filling in Story properties on entities gives the Assistant more to work with.

For navigation: "Go to the scene where Kira and Marcus meet" works if you've written meaningful scene descriptions. Vague entity names make navigation harder.