Tunori documentation
Tunori gets your tasks done by AI. You describe what you need in plain language — as you would say it to a colleague — and an AI agent does it, using the accounts and tools you have connected.
There are no flowcharts and no workflow builder. If you can write the task down, you can automate it.
How it fits together
Four ideas cover almost everything:
- Agents — an agent is a reusable AI worker. It has a name, instructions describing what it does, a model, and the tools it is allowed to use.
- Chats — where you talk to your agents and they report back. Every run of an agent, including automated ones, produces a chat you can read afterwards.
- Integrations — the accounts you connect, such as Gmail, Google Drive or Xero. Connect once, and your agents can act in them.
- Triggers and schedules — how work starts without you: at a set time, or the moment an email arrives or a file lands in a folder.
What a task looks like
Tasks are written as ordinary sentences. These are real examples:
When I get an email with a PDF invoice, save it to my Drive in a folder for that year and month.
Every weekday at 7am, email me a rundown of today's meetings with the attendees and Meet links.
Every Monday at 8am, email me the overdue invoices in Xero with the customer, amount, and how late they are.
Each of those is an agent with instructions, plus either a schedule or a trigger.
Where to start
If you are new, follow the Quickstart — it walks you through creating an agent, connecting an account, and getting real work out of it.
If you want to know what Tunori can actually reach, browse the connector reference. Every connector lists its tools and what each one does.
Staying in control
Two things are worth knowing early:
- You decide which tools an agent may use, and you can require your approval before any particular tool runs. See agents.
- Usage is charged against credits in euros — token usage plus a small fee per tool call. Nothing runs when your balance is empty. See billing and credits.