// answers

The words we use, explained.

Straight answers, no jargon — the vocabulary of working with AI that actually remembers.

// the category

What is a collaboration OS?

A collaboration OS is the operating layer where humans and AI work together as genuine workmates — same context, same memory, same projects, same stakes. It is not a workspace with AI features added, and not a chatbot with folders: the collaboration itself is the architecture.

The term exists because the current categories don't fit. Workspace tools organize your work but don't participate in it. AI assistants respond but don't remember. A collaboration OS is built for the relationship between the two — context earned once, held permanently, and worked by both sides.

Onnie is the first collaboration OS: tables and pages as the shared context layer, Onnie and Onniebots as the agent layer, routines and tasks as the execution layer.

What is context debt?

Context debt is the cumulative cost of re-explaining your work to AI — every new session, every tool switch, every re-opened project. You re-paste the background, re-describe the goal, re-orient the tool. Each instance costs minutes; across weeks it costs the momentum that separates projects that ship from projects that stall.

The debt compounds invisibly. Most people don't stop using AI because it's bad — they stop because the overhead of context swallowed the benefit. That exhaustion is context debt coming due.

Onnie eliminates it structurally: context lives in the workspace — tables, pages, memory — not in the chat window. You earn it once. It never resets.

What is the setup trap?

The setup trap is the belief — enforced by most productivity tools — that you must become a system architect before you can be a doer. Install the template. Configure the workspace. Build the automations. Connect the integrations. Only then, maybe, do the actual work.

The setup never ends, because the tools are built for maximum flexibility, which means maximum configuration. The people caught in it aren't doing it wrong — the mechanism is the problem.

Onnie is built against the trap: you start working in your first session, and the workspace forms around the work instead of before it.

// inside onnie

What is an Onniebot?

An Onniebot is a specialist AI agent you create in Onnie — with its own name, personality, tool access, and memory scope. Onnie is the generalist; Onniebots are the team of specialists you build around it: one for client emails, one for your content pipeline, one for the weekly review. They read your tables and pages, run on demand or on schedule, and remember their own domain.

What is a routine in Onnie?

A routine is a scheduled, automated workflow — the daily brief, the weekly review, the recurring client update — that runs without you having to ask. Routines that use AI reasoning spend credits; function routines (deterministic code, no AI) always run free.

What are tasks in Onnie?

Tasks organize human and agent work in one shared list, with an audit trail of what was done, by whom, and when. It's not a to-do list — it's the shared record of the collaboration: you hand a task to an agent the way you'd hand it to a teammate, and review it when it comes back.

What are tables and pages in Onnie?

Tables and pages are the context layer of the workspace — structured data and rich documents native to Onnie and readable by every agent. They hold the persistent context for the work, so nothing needs to be pasted into a chat window; agents, routines, and tasks are where the work itself happens.

What is included capacity in Onnie?

Each plan includes a shared workspace capacity pool for AI operators and automations. Relative size (for example Pro is ~8× Free) and optional notional value describe the pool — not a live chat meter. AI operator seats expand who can burn that pool and, on Pro/Business, raise the allotment. Function routines that do not call AI stay free. When the pool is empty, AI reasoning hard-stops unless an admin enables extended capacity (opt-in real dollars) or adds seats.

What is the amber chip?

The amber chip — [● Onnie] — is the visual signal that an agent is present or active in the workspace. It appears on chats, tasks, and routines an agent is working on, and never on things a human made alone. It's how you know the collaboration is real: when the chip is amber, someone's actually in it with you.

Meet the workspace these words come from.

Start working with OnnieSee the product