Skip to main content

What this helps you do

Trust an agent answer for the right reason — because you can see what it read — and set each agent’s boundaries so safe work runs at full speed while sensitive actions wait for you.

Read the sources behind an answer

Every substantive agent answer carries the material it worked from.
1

Open the sources

On a suggested reply, open Sources to see the records the agent used — property facts, documents, and conversation history each appear as their own source. A reply with no attached material shows “No sources are attached to this reply.”
2

Check what each claim rests on

Match the answer’s specific claims to the listed sources. Sources used names what actually informed the reply, not everything the agent could reach.
3

Inspect a full run

For agent work beyond a single reply, the run’s Evidence shows what the agent did and found step by step.
If a claim has no matching source, or the source is a document you know is out of date, correct the record first — see Fix wrong AI information — rather than editing the one answer.

Control what runs immediately

An agent’s boundaries live in its Access & Safety settings.
1

Set tool permissions

Every tool the agent can use is Allowed, Ask first, or Off. Ask first means the agent can draft the action, but a human must confirm before it runs.
2

Set work-area access

View and Change access are set separately per work area, so an agent can read one area while only proposing changes in another.
3

Keep deliveries reviewed

Outbound messages follow the reply flow’s Approve & send control. For the situations that always deserve review, see Approve a sensitive message.

Where the line sits by default

The five action classes in Understand the five action classes explain the model behind these controls: reads and drafts are safe and run immediately, while deliveries and spending pause for a person. Agent permissions apply that model per agent and per tool — tighten a specific agent’s boundaries with Ask first or Off without slowing down every other agent in the workspace.