Letting the AI do things (propose → approve)

The dealer AI can do real work for you: add a vehicle, move a lead, start a deal, even record a loan payment. But it never changes anything on its own. It proposes the change as a card, you review it, and only your Approve (or a plain "yes") makes it happen.

How it works

When you Approve, the card runs the real action: the same one the manual screens use, with the same rules and audit trail behind it. On success the card flips to an Approved badge, and for a new vehicle, lead, or customer you get a View link to jump straight to the record. (Other actions, like a status change or a loan payment, simply show Approved, with no View link.)

If you Reject instead, the card collapses to a Dismissed badge. Rejecting only stops a card that's still waiting. It never reverses something you already approved.

Approve by just saying "yes"

You don't have to hunt for the button. If the AI's last message proposed a single change, you can simply reply yes (or "ok", "do it", "go ahead", "approve") and it runs. Reply no (or "cancel", "skip", "nevermind") to dismiss it.

Autopilot: skip the approval for routine changes

If you own the dealership, you can pre-authorize specific routine actions so the AI applies them the moment it proposes them, with no approval tap. Turn it on under Settings → AI assistant → Autopilot and tick the actions you trust it with (creating tasks, updating lead statuses, changing a price, and so on).

Four things stay true no matter what you tick:

• Money and irreversible actions always ask first. Recording a payment, marking a deal sold, sending an email or text: these can never be put on autopilot. The setting won't offer them, and the server refuses them independently.
• Reading outside content pauses autopilot for that reply. If the AI read something written by someone outside your team while working on your ask (a lead's message or contact details, an attached document, external vehicle data), any action from that reply comes as a normal approval card instead of applying automatically. This is a safety measure: text a stranger typed into your website can never trigger an unattended change, no matter what it says.
• Everything is logged. An autopilot change shows in the activity trail marked as applied automatically, so you can always tell what the AI did on its own versus what someone approved by hand.
• Nothing gets lost. If an autopilot apply fails for any reason, the proposal stays as a normal approval card and you approve it yourself.

Only the owner can change autopilot settings, and each staffer's role limits still apply: the AI acting for a salesperson can only auto-apply what that salesperson could do themselves.

Background jobs: hand it bulk work

For work too big for one reply ("reprice every SUV over 60 days old", "clean up the listings missing photos"), the AI can run a background job. Starting one is itself an approval card showing the job's name and exactly what it will do. Once you approve, the job runs on its own in segments, posting its progress back into the same chat.

A job never gets special powers: every change it wants to make goes through the same approval cards (or your autopilot settings) as if you'd asked in chat. When a step needs your approval, the job pauses, you get a notification, and it continues automatically after you decide. You'll get a notification when it finishes, and asking "how's my job going?" gives you the status any time.

Schedules: standing work on a clock

For work you want done on a rhythm rather than once ("every weekday at 7:30, check for leads nobody has touched and brief me"), create a schedule. Ask the AI for something recurring, or manage them under Settings → AI assistant → Schedules: pause, edit, delete, see each run's history, or hit Run now to try one immediately. Times are your dealership's local time.

A schedule is just a clock on the background-job machinery, so nothing changes about safety: each run's proposed changes still arrive as approval cards (or apply via your autopilot settings), and the run's briefing lands in your AI chat marked as an update so you can't miss it. Creating a schedule always needs an explicit approval, even with autopilot on: standing behavior is something you say yes to yourself. Schedules pause themselves and tell you why if their creator leaves the team or three runs in a row fail, and owners and managers can have up to ten.

Editing before you approve

The card is editable. You can change the values the AI suggested before approving: a price, a status, a description, options checkboxes, and so on. Money fields accept "18000", "18,000", or "$18,000.50"; they're cleaned up for you.

What you can't change is which record the action points at. The vehicle, lead, or customer being acted on shows as a read-only line on the card. That's on purpose. It means an approval can never be retargeted to a different (or another dealer's) record.

What the AI can do

There are 21 actions today, grouped by area:

• Inventory: create a vehicle, edit it, change its price, change its status, publish it, rewrite its description.
• Leads: create, change status, assign to a salesperson, convert to a customer.
• Customers: create, edit.
• Tasks: create, assign, set status, add a comment.
• Deals: create a deal, move a deal through its stages (including mark sold).
• Title: move title work through its stages.
• BHPH: record a loan payment.
• Memory: remember a fact for your own future chats.

Who can approve what (role gating)

Each action is gated to your role, and the AI only ever offers you actions your role is allowed to perform:

• Owner / Manager: everything.
• Sales: inventory, leads, customers, tasks, deals, title work. Not loan payments.
• Accounting: customers, tasks, title work, and recording BHPH loan payments. Not inventory or the sales pipeline.

Saving a personal Memory isn't restricted. Every role can do that, since it only affects your own future chats.

The gate is checked twice: once when deciding what the AI can even offer, and again the instant you approve. So a proposal for something your role can't do is refused at approval with a message like "Your role can't perform this action."

FAQ

Will the AI ever change something without me approving?

No. Every write is a proposal you must confirm, either by clicking Approve or by replying yes to a single pending card. There is no "trusted" path that skips this.

Can I undo an approval?

The action runs the same as if you'd done it by hand, so undo it the same way you would manually. Change the price back, say, or move the status again. Rejecting a card only stops a pending proposal; it doesn't reverse one you already approved.

I clicked Approve and it said the action can no longer be applied.

If a platform admin has turned AI off for your dealership, pending proposals can't be applied anymore, even by their card or a "yes." The message reads "AI features are turned off for this dealership, so this proposed action can no longer be applied." Once AI is re-enabled (contact support if you're unsure), the AI can propose it fresh.

What does "Edited values are invalid" mean?

A value you typed on the card didn't pass validation, and the message names the field. Fix that field and Approve again; the rest of the proposal is preserved.

Does approving leave a record?

Yes. Every approved and rejected action is written to your audit log, tied to your user, so there's always a trail of who confirmed (or declined) what.

Can the AI act on another dealer's records?

No. Everything is scoped to your dealership, and the record an action targets is locked on the card and can't be retargeted.