Create a saved agent

Who can do this

Any member with the User role can ask Ronja to create a Saved Agent. Creating one in a shared feature, and every later update or delete, pauses on the in-chat approval strip; non-admin changes route to the proposal queue for an admin’s decision.

A Saved Agent is a reusable package — a prompt, a model tier, tool grants, and a pinned set of resources it may touch — that Ronja can run on demand. Like most resources, there is no create form and no sidebar entry: Saved Agents are created and edited only by asking Ronja in a conversation. The Agents page is a read-only catalog.

Create one

1. Open an exploration and get the task working interactively — the prompt, the data, the output you want.
2. Ask Ronja to save it. In the product’s own words: “ask the agent in a chat to save its prompt + grants as a reusable Agent”.
3. Approve the action on the approval strip when Ronja pauses for confirmation.
4. Find the result from the link in chat, or later on the Agents page — filter by Live / Drafts / Proposed / Archived and by model tier Fast / Standard / Mega.

Caution

Saving into a shared feature as a non-admin creates a proposal — an admin approves it before the Saved Agent goes live. See Propose and review changes.

Test it

1. Open the Saved Agent’s detail page.
2. Describe a task in the Try this Agent panel — the placeholder suggests “Summarise this week’s pipeline health.” — and optionally attach inputs (tables, files, notes, workflows, and more).
3. Click Run and watch the live run card. Every run is traced — see Monitor runs and traces.

The read-only detail page: test runs here, edits happen in chat.

Edit it

1. Click Open in exploration on the detail page — as its banner puts it, “Editing an agent happens in chat.” (This opens a Build-mode exploration, so it needs Build mode enabled for your account.)
2. Ask Ronja to patch the prompt, references, or tool grants. The change goes through the same approval or proposal lane as creation.

Where Saved Agents run

• From any exploration — ask Ronja to run it.
• From automations — Email and Webhook triggers require a Saved Agent action; Schedule and Table triggers can use one too.
• From data apps that are allowed to dispatch it.

Saved Agent or a plain exploration?

Use a plain exploration for one-off, interactive work — you steer every turn. Package a Saved Agent when the same job should run repeatedly or unattended: it always runs with the same prompt and model tier, and its references pin exactly which tables, workflows, notes, secrets, data apps, MCP servers, or features it may touch — nothing else. See Exploration vs Saved Agent.