AI Assistance / Playground
Every frontier model behind one login, with the price under every answer.
The Playground is a plain chat with the models your administrator allows. No brand data: the model sees this conversation, the files you attach, and your instructions. Compare three at once, get documents back, and read the cost under each reply.
Demo workspace. Invented brand and figures.
Same question, three models, three prices.
Compare. One message, up to three models, three prices. Keep the answer you prefer and the thread continues from there.
Pick a model. Every model carries its capabilities in the picker: whether it sees images, whether it can create files. Switch mid-thread and the conversation is replayed to the new one.
Instructions. A system prompt and a temperature for this conversation only. An administrator can lock both for the whole organization.
Admin. The administrator decides which models members may use, whether sampling is locked, and how much each member may spend in the Playground per month.
Documents in, documents out.
Drop a contract, a spreadsheet, a deck. The text is extracted and handed to the model with your question. Ask for a summary as a Word file or the figures as an Excel sheet, and the model creates the file during its answer.
Uploads go straight to storage, so a large file never waits on the chat. Files stay in the conversation until you delete it.
In
What you can attach
PDF, Word, Excel, text, Markdown, CSV, JSON, code, and images. Up to 20 MB per file and 20 files per conversation. Documents are read as text; images go to models that can see them.
Out
What the model can create
Word, Excel, CSV, PDF, Markdown, text, JSON, HTML, PowerPoint, and code files, made by the model during the answer and listed under it to download.
Export
Any answer, seven ways
Word, PDF, Markdown, text, HTML, a table as CSV, tables as Excel. Or the whole thread as one Markdown file.
The administrator holds the keys.
Per organization. Leave it open, restrict it to a shortlist, or switch the Playground off entirely.
Fix the temperature and the answer length for everyone, so a member can’t change them.
A ceiling in dollars, counted from the first of the month. When it is reached, new messages are refused until next month.
Skills you or your organization wrote apply on top of the conversation’s instructions.
No seat. Tokens, from the same wallet.
There’s no Playground subscription. Each answer is metered in tokens and paid from the same prepaid wallet as the rest of the product. The billed price is printed under the answer, and the month’s Playground total sits in the left rail.
Three ceilings apply, independently: your daily cap, the organization’s monthly cap, and the Playground allowance the administrator set for you.
Under every answer
Tokens in and out, and the billed dollars.
In the rail
This month’s Playground spend, live.
In the ledger
Who, when, which model, exact cost.
The same data, one door over.
Nothing here is an integration. These run on the same account, the same brand, the same ledger, so a finding on one page becomes work on the next.
Not built yet, said first
- Compare keeps the first alternative as the thread until you pick another.
- Two small models can’t create files; vision depends on the model, and the picker says which.
- Conversations are yours alone. There is no sharing between colleagues yet.
The catalog lists every agent as built, partial, or not built. Checked against the product on September 3, 2026.
Usage is metered in tokens from a prepaid wallet, with no seat fee. The rates are on thepricing page.
One login for every model your team asks for.
Open an account, switch on the Playground, and the model list is there. Each answer prints what it cost.
No subscription. No seat fee. No card needed to request an account.