Your Google Ads, audited every morning — in your chat.

How the daily routine works

Three steps. About ten minutes the first time to connect and pick an install path, a minute or two to schedule it, and nothing to do most mornings after that except read.

1. Connect Google Ads. One click, your own Google sign-in — connect at app.adcopilot.cloud. It reaches only the accounts you grant, and it can never delete. Already connected? Skip to the next step.
2. Get the playbook. Pick the built-in morning-auditprompt from your client's prompt picker — no install, it's part of every AdCopilot connector and knows the full audit sequence and safe-change etiquette below. (Power users on Claude Code or claude.ai can load the adcopilot-daily skill instead — covered just below.)
3. Schedule it.The skill walks you through setting up a daily run and hands you prewritten, approval-gated task text to paste — it can't create the schedule itself. Also covered below.

The zero-install way: the MCP prompt

Every AdCopilot connector already exposes the whole checklist as a ready-made MCP prompt named morning-audit— no skill, no plugin marketplace, nothing to install. Select it from your client's prompt picker (Claude, ChatGPT, Copilot, Gemini CLI, or any other MCP-capable client) and it runs the same six checks. This is the path we recommend for almost everyone.

Prefer a skill? Load it yourself

On Claude Code or claude.ai you can load the adcopilot-dailyskill, which packages the same playbook plus the safe-change etiquette. It isn't on a public marketplace — email [email protected] for the SKILL.md, then on claude.ai use Customize → Skills → Create skill and paste it in. Invoke it with /adcopilot-daily, or just ask for “my AdCopilot morning audit.” It does the same thing as the prompt above.

Setting up the schedule

Here's the honest part: the skill can't create the schedule itself — nothing outside your own Claude account can. What it does is walk you through it and hand you the exact, prewritten task text to paste, so the schedule you create already says “propose it, don't apply it” in plain words:

• Claude Code: run /schedule in any session, choose Daily at whatever time suits you, and make sure the AdCopilot connector is enabled for the routine.
• Claude Desktop: sidebar → Routines → New routine (Local), same daily time, same pasted text, permission mode left on approval — not auto-approve.

Run the audit once by hand first, so you see the report format and can tell it your monthly plan cap. From the next morning on, the routine runs the audit and queues proposals; you just read and reply.

What the morning audit covers

Six checks, in this order, for every account you've connected:

That's the same sequence a one-off AI audit runs — the only difference here is that it runs itself, on your schedule, instead of waiting for you to ask.

What lands in your chat

Every run ends with one compact table per account and a plain verdict — OK (nothing to do), WATCH (noted, no change yet) or ACT (a proposal follows):

Account: Example Co. — 1234567890 (USD)   Window: 2026-07-21 to 2026-08-20

Check                 Result                            Verdict
Spend vs plan cap     $2,140 MTD of $2,500 cap           OK
Wasted spend          $312 on 6 zero-conversion terms    ACT
Negative candidates   4 off-intent terms ($188)          ACT
Disapprovals          1 ad disapproved                   ACT
Pacing                projecting $3,050 — 122% of cap    WATCH

Illustrative example — not data from any account, and not a promise about what your own report will find. Each ACTline becomes a specific, approvable proposal underneath the table: the account, the campaign or keyword, the exact change, and what it's expected to do. Nothing above has touched the account yet.

The two rules it can't break

Whether the audit runs by hand or on a schedule, the same two rules hold — a routine that could quietly get around them on a timer would be worse than not having one at all:

1. Approval-gated.The scheduled run performs the audit and queues proposals — it never applies a change on its own. Every mutation is proposed first and only applied after you reply yes, in that session. There is no “while you sleep” mode, and no setting that turns one on.
2. It can never delete.The connector physically cannot remove anything — the delete tools aren't wired into it at all, and the server refuses any call that would set something to removed. The safe equivalent it reaches for is pause, undone in a click. A genuine deletion stays a Google Ads UI action, on you, by design.

Every applied change comes back with how to undo it — almost always the exact opposite call, like re-enabling a paused campaign. The one honest exception is a negative keyword: the connector can add one, not remove it, so reversing that means the Google Ads UI, and it says so rather than pretend otherwise.

Frequently asked questions