Scale your marketing with the team you have. Agents test and improve campaigns daily, inside limits you set.
Send a “running low” note to first‑time buyers
1,376 of 1,860 get this email after your limits
Ad dashboards count revenue, but you keep the margin. Agents judge each sale by what it’s worth to you: order value, margin, or any value you send with the event.
Agents do the daily work: testing, checking and adjusting spend. You set the direction, make the calls that matter, and read what happened.
Tell each agent what you want, what it must never do, and what a result is worth to you.
Each proposal shows what it changes, why, and the checks it passed. You choose which kinds of change wait for you.
Launch three creatives for the pour-over kit
+$40 a day for 14 days · $560 total · 3 ads go live on Meta
WhyOur cost per click rose 10 percent over six weeks.
Each agent explains what changed and why, in plain English. Reply in a sentence to steer it.
What your agents did overnight, what needs your decision, and the numbers they answer to.
Heraldic
Today's lead · New customers
The Holiday Blend carries the week
First orders rose 18 percent to 71, and each cost $3 less. I moved budget toward the Holiday Blend and gift sets, where we have deep stock and the best margins.
By the New Customers agent · filed 6:02 a.m.
Awaiting your decision
⁂ From the other desks
The week in numbers
This month$7,742 / $10,000
Agents write the ads and emails, then answer for the results, measured on your own sales data.
Agents never touch your accounts directly. They propose changes, your rules decide what goes through, and every rule runs again before anything changes.
No. You connect each account through the platform’s own sign-in (OAuth), so your passwords never reach us. Agents never hold credentials of any kind: they propose changes, and a separate service makes them after checking your rules. You can revoke access at any time.
An agent can’t make a change past your hard limits. Spend caps, the 20% limit on each budget change, contact caps, consent and suppression lists, and banned phrases are checked in code when an agent proposes a change, and again right before it’s made. Claims are checked by the brand review agent against your approved claims library, and a claim without a source can’t be used. Every action is logged with its reason, and one switch stops every agent.
Pricing isn’t set yet. Your ad spend goes straight to the ad platforms, as it does now.
A wide range across ads, email, store and CRM, each connected through the platform’s own sign-in, plus an events API for anything else you count, such as a booked demo or a signed contract.
The platforms’ automated campaigns are good at finding buyers inside their own platform, from its data and your product feed. But each one sees only that platform, sets its own limits and reports its own results. Agents here work across the channels you connect, email included, under one set of rules you control. They judge results on your own conversion data and explain every decision. To an agent, an automated campaign is a campaign like any other: it can propose budget, pause and resume changes for it.
Your email platform’s agent works inside that platform, on its numbers. Agents here run your ads and your email together, under one set of limits enforced in code, judged on your own conversion events, with every proposal and check on the record.
We don’t take the ad platforms’ word for it. Each platform credits itself for any sale it touched, so their totals overlap and run high. Agents measure against your own sales data instead, compared with a baseline from your history. By default, each email send holds back a small group, so across sends you can see what email adds. For ads, when you have the volume, agents propose tests that leave out a region or an audience. When there isn’t enough data to tell, the report says so.
Your work email is all we need to start.