Product

Observability and Governance

Writes and other sensitive steps can wait for a person. Every run leaves a record: what happened, what changed, and why. Admins can see usage and audit history for the workspace.

From capability to everyday work

Observability and Governance, in practice.

Writes and other sensitive steps can wait for a person. Every run leaves a record: what happened, what changed, and why. Admins can see usage and audit history for the workspace.

Use it for
Work that should move from a draft to a change in another system, with a person reviewing the action.
Start with
Connect or receive access to the account, then keep the project in safe mode while evaluating.
Read the setup guide
Illustrative workflow Sample data
The request

“Draft a customer check-in, then ask me before sending it.”

  1. The agent drafts the message using the available context.

  2. An unapproved integration action in safe mode waits for review.

  3. Approve once, deny, or explicitly pre-approve future calls.

Awaiting your review

Review point
Action
Send customer follow-up
Account
Your connected email account
Review
Check the recipient and message before approving

The requested action waits at this review point.

Approvals & control

Review actions before they run

On each project, tools can be ask-first or automatic. Ask first is the right default for anything that emails a customer, writes to a CRM, deploys, or spends money. Automatic is fine for read-only lookup once you trust the connection.

When an agent needs permission, a card appears in the thread and in Notifications. Approve, decline, or continue with a different approach. Declining stops that action.

Run history

Follow workflow execution end to end

Each flow run has a history you can inspect: what ran, what failed, and what came out. Agent threads leave artifacts — documents, diffs, schedules, pull requests — as the reviewable record of the work.

You do not need a separate admin console for everyday review. Most of it happens in the thread, in Notifications, and in the run you already opened.

Usage

Understand workspace activity

Usage is meant to answer what the workspace ran, not how to tune a model provider. See tokens and cost by model kind: faster, default, and thinking.

If a project is expensive, look at how often it uses deeper thinking models or long agent threads, then tighten approvals or split experimental work into a personal project. Audit logs give admins a view of sensitive actions.

Before you try it

Questions for your evaluation.

Work that should move from a draft to a change in another system, with a person reviewing the action.

Connect or receive access to the account, then keep the project in safe mode while evaluating.

Only the person who started the run can approve or deny its paused action. Allow Always pre-approves that action for that user and project.

Unlimited inference.
Company memory.

Connect your tools, ask your first question in a project, and watch memory, spend, and visibility stay in one place—not scattered across personal chats.

$15 / user · Unlimited AI
Q4 launch› Launch dashboard
Sara Castillo

@kluff build a launch dashboard from HubSpot and the Q4 budget sheet. Refresh it every morning.

Kluff

Done. Signups come from HubSpot, spend from the Q4 budget sheet. It refreshes at 7:00 AM.

v2 adds the channel split you asked for.

Maya Ruiz

Can we flag any channel over $40 per trial?

Kluff

Added. Paid social is flagged.

Q4 launch dashboard
Q4 launchHubSpot + Q4 budget sheet · refreshed 7:00 AM
Live
Signups1,284+18% vs last week
Trials started31224% of signups
Spend$8,420of $12,000 budget
Daily signups
MonTueWedThuFriSatSunMonTueWed
Send the renewal to Harbor Foods?

It sends from your Gmail, as you, with the draft attached. Nothing else leaves the project.

SENDGmail · Dana Reyes, Harbor Foods purchasing
ATTACHGoogle Drive · Harbor renewal 2026.docx
Finance check done

Ana Chen confirmed net 45 at 9:18 AM. Your rule: every customer email waits for you.

Sent · logged to the project