What an AI media buyer is, and what it is not
A media buyer's job is allocation: which platform, which campaign, how much, and when to change it. Adease does the analysis half of that job continuously — pacing against the monthly budget, marginal return per platform, campaigns that are budget-limited while others waste — and hands you the allocation decision as a card. It does not spend on its own. That is the whole design, and it is why agencies who have been burned by platform automation trust it with client budgets.
Guardrails are enforced, not suggested
Spend guardrails — the maximum a budget can move in a day, the ceiling on any single campaign — are applied server-side on every write. An approved change that would breach them is refused, so a hurried click at 6pm cannot double a budget. The agent knows the guardrails too and proposes inside them, which is why the card above shows the limit next to the change.
Cross-platform is the point
Where the next pound should go is only answerable if Meta, Google, TikTok, LinkedIn and Pinterest are in the same view. Adease keeps them in one campaign table and one conversation, so "move £2,000 into whatever has headroom" produces a plan across platforms, with the trade-offs explained, rather than five separate reports to reconcile.
Where it fits
A good fit if you
- are accountable for a monthly budget across more than one platform
- want reallocations proposed daily but decided by you
- have been burned by platform automation and want a hard ceiling on changes
Not a fit if you
- want an agent that acts on its own without review — Adease will not do that
- only run one platform and are happy with its native rules
- work on Linux, or need a dashboard a distributed team opens in a browser
Questions people ask
Can it change my campaigns without asking?
No. There is no autonomous write path to a live ad account. Every change the agent proposes is queued in Approvals as a diff and applied only once a person approves it, inside the spend guardrails set for that workspace. Rejecting a proposal sends nothing to the platform.
How do spend guardrails work?
Guardrails are limits you set per workspace — the maximum a budget can change in one day and the ceiling on any single campaign. They are enforced on every write, so an approved change that would breach them is refused rather than applied. The agent reads the same limits and proposes inside them.
Which advertising platforms does it work with?
Meta, Google, TikTok, LinkedIn and Pinterest ad accounts, plus a Shopify store as a product catalogue. All of them sit in one campaign table and one conversation, so a question or a change can span platforms.
Which AI model is behind it?
Adease is built on Anthropic's Claude models. The agent that reads your campaign data, investigates performance and drafts changes runs on Claude. Adease is an independent product made by Adease LTD.
What does it cost?
Adease is free to install and needs no card. The Pro plan is $50 per seat per month with unlimited ad accounts, clients and campaigns. Max is $200 per seat per month with five times the agent token allowance. You pay per person, never per account or per pound of spend.