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
• Workflow diagnosis -- look at a workflow of yours that will not run, including the one behind your last failed job, and say in plain terms what is wrong with it

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

Asking what to do next

Ask the Assistant "what should I do next?" and it answers from where you are standing. If the page you are on has open work, that is what it offers first -- the character, location or scene in front of you, not whichever one the plan happens to list first. It then names at most one alternative, so you get a choice rather than an order: finish this here, or start that instead. Characters, locations and props have no required order between them, and the Assistant will not invent one.

When the page you are on is finished, it says what is open elsewhere, so you are never told there is nothing to do while work remains. If the page is waiting on something earlier -- a scene with no shots yet, say -- it names the thing that has to happen first. It is reading the same open work the guide bar at the top of the page is showing you, so the two always agree.

Watching it work

While the Assistant is working, a status line above the chat box says what it is doing right now -- reading a character, updating a prompt, asking one of its specialists. On a task that takes a while it keeps updating, so you can see it is still going rather than wondering whether it has stopped.

If a step is taking a long time, the status line says which step and how long it has been running. That is normal for work that involves a lot of reading; if it stalls with nothing new for a long stretch, the Assistant will tell you the turn ended rather than leaving you waiting.

Nothing changes behind your back. Every value the Assistant writes, it shows you: it takes you to the page holding that field, scrolls to it, and the field pulses blue as the new value lands. Several changes at once arrive one at a time, about a second apart, so each reads as its own beat and you can stop it part-way. This holds wherever the value lives -- a character or scene property, a recipe step's input on the Actions tab, a plan item it marks done, a character it promotes to major -- and whether the Assistant did the work itself or handed it to one of its specialists. If the Assistant tells you it changed something, you saw it change.

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.