Product · Control and log

Autonomy with handbrake.

Each action of each agent is recorded with name, permission and time. Whatever you decide needs approval, ask for it. And everything an agent does can be reversed.

Chat Agent · permissionsdeclared
Opportunity boards2/7
Calendars and resources5/9
Form templates3/6
Out of reach
Win or loseDelete contactsChange schedulesEdit closed answer

Waiting for approval · out of catalog price

Conversation · +52 55 1234 5678 · 11 min ago
Permissions

What an agent can do and what remains on the human side.

This is the default distribution. Everything can be adjusted by board, by calendar and by role, but nothing opens without you opening it.

ActionAgentteam person
Reply in chatYes, within your catalogYeah
Create and edit contactsYeahYeah
Merge or delete contactsNoYeah
Create and move opportunitiesYes, by authorized boardYeah
Mark won or lostYes, if the board allows itYeah
Schedule and reschedule appointmentsYes, within the configured scheduleYeah
Create resources or change schedulesNoYeah
Save form responsesYeahYeah
Edit a closed answerNoNo
Save configuration changesProposes; does not saveYes, upon approval
Control

They do the work. You remain in control.

You'll never wonder what happened while you weren't looking. Each action has an agent, time and record, and all can be undone.

Activity logLive

Calendar Agent Roma branch availability changed

Calendar · Dr. Ruiz

Deals Agent moved an opportunity to Submitted Proposal

Sales Dashboard · $2,400

Chat Agent requested human support for an out-of-catalog price

Conversation · +52 55 1234 5678
Requires approval

Forms Agent submitted the medical history form

Contact · Mariana Cruz

Reminders Agent set a reminder 24 hours before

Appointment · tomorrow 5:00 pm

Contacts Agent created the profile and labeled it New lead

Contact · Mariana Cruz
Filter by agent, module, record or date range.
Permissions Chat Agent
Opportunity boards3/7
Writing on boards2/7
Schedulable calendars4/5
Win/lose0/7

Winning and losing is out of your reach: that decision is still yours.

Agent on standbyLaura has been in control since 10:41
Permissions per tool

Each agent declares what it can touch: "3 of 7 boards · writing on 2." Reading, writing and win/loss actions are granted separately.

Approvals where it matters

Out-of-scope work does not run: the agent stops, notifies the owner with the reason and wait time, and waits for approval.

Take control in one click

Turn off AI and write without leaving the thread. The agent steps aside and resumes when you reactivate it.

Sandbox before production

You test personality, playbooks and permissions without spending real messages or touching a record of your operation.

All reversible

Each action is linked to the record that it modified. If something should not have happened, it is undone from the log itself.

Account status

One screen shows what's ready, what's broken and what's left to configure, with a suggested next step.

Human takeoverApprovals where it mattersSandbox without spending messagesAll reversible

Autonomy, but with your hand on the brake.

Start with the agent requesting approval for everything, then expand permissions when its work earns your trust.

See all five modules