# Can ChatGPT Create a Google Ads Campaign End to End?

With a write-capable connector, yes: campaign, ad group, keywords, RSA and budget in one conversation — paused until you enable it. The real sequence.

Questions · Published 2026-08-10, updated 2026-11-13.

> Yes — with a write-capable MCP connector, ChatGPT can build a complete Google Ads campaign in one conversation: campaign, budget, ad group, keywords, responsive search ad and assets, each a tool call AdCopilot proposes first, with the campaign paused by default so nothing spends until you enable it. Two decisions should stay yours regardless: the budget ceiling and the conversion goal. In ChatGPT the connector comes as the AdCopilot plugin, and whether you can install and use a plugin depends on your ChatGPT plan, workspace and region. Without a connector, ChatGPT can only draft a plan for you to build by hand.

There are two versions of "ChatGPT built my campaign". In one, it wrote a
nice plan and you spent the afternoon clicking it into existence. In the
other, the whole campaign — structure, keywords, ad and all — exists in
your account by the end of the conversation, built in seconds through tool calls AdCopilot proposes first, then parked paused for your review. The second version
is real, and this page walks its actual sequence.

## The answer and the required setup

ChatGPT creates campaigns end to end once two conditions hold: your ChatGPT
account can install and use the connector's plugin (OpenAI's
[help page](https://help.openai.com/en/articles/20001256) says that depends
on your plan, workspace, role and region, and in a work workspace the admin
also decides which of a plugin's actions run), and the connector exposes
write tools. Read-only connectors analyse; a write-capable one such as
AdCopilot builds. Added by hand as a custom MCP server instead, it falls under
OpenAI's [rules for those](https://help.openai.com/en/articles/12584461): full
MCP, tools that change things included, on Business, Enterprise and Edu, and
read and fetch only on Pro. The
[ChatGPT connection guide](https://adcopilot.cloud/connect-chatgpt-to-google-ads) covers both
conditions; whether ChatGPT can "manage" ads more broadly is
[its own question](https://adcopilot.cloud/questions/can-chatgpt-manage-google-ads).

## The build sequence: what gets created, in what order

A campaign is a tree, and the agent builds the whole tree in dependency
order — each step one or more tool calls, and your AI client asks before each one runs if it is set to ask before AdCopilot's write tools: 1. **Campaign** — name, type (search or
   [Performance Max](https://adcopilot.cloud/performance-max-ai)), bidding, daily budget.
   Created paused.
2. **Ad group** — one per keyword theme, with a default CPC bid where
   manual bidding applies.
3. **Keywords** — with explicit match types, plus the first negative
   keywords.
4. **Responsive search ad** — up to fifteen headlines and four
   descriptions, drafted in chat for your edits before any tool call.
5. **Assets** — sitelinks, callouts, structured snippets, linked to the
   campaign.
6. **Targeting** — geo targets and location exclusions, ad schedule,
   device adjustments where wanted.

Then the agent reports the inventory: everything created, with IDs. The
campaign sits paused until you enable it in the UI — the build is a
reviewable draft with real structure, not live spend.

## The two decisions the AI should never make alone

An agent will propose defaults for everything, and for most of the tree
its defaults are fine. Two inputs are different in kind, and a
well-prompted build states both up front:

- **The budget ceiling.** How much this campaign may spend per day is a
  business decision about risk and cash, not an optimisation output.
  Give it as a constraint; never accept it as a suggestion.
- **The conversion goal.** What the campaign optimises toward — which
  conversion action, lead quality versus volume — decides what "working"
  means. An agent can describe the trade-offs; only you know which one
  the business wants.

Everything else — structure, match types, copy themes, scheduling — is
legitimately delegable, because everything else is recoverable and
reviewable.

## A worked example: brief to built in one conversation

A realistic exchange, compressed:

**You:** "In account 123-456-7890, build a search campaign for our
emergency plumbing service in Leeds. Budget forty a day in account
currency, Maximise conversions — and confirm the phone-call conversion
action is live before you start. Keep it paused."

**The agent:** proposes the campaign call — you approve. Proposes one ad
group per theme (emergency call-outs, boiler repairs), each with phrase
and exact keywords pulled from the language on your landing page — two
approvals. Drafts the RSA in chat; you cut the weakest headlines, tighten
one claim; it creates the ad — one approval. Sitelinks for pricing,
reviews and contact — one approval. Geo target Leeds plus surrounding
postcodes — one approval.

**The close:** an inventory with IDs, a paused campaign in the account,
and a reminder of the one thing it cannot do: enable is your click, in
the UI, after review.

## Common failure points — and how to avoid a half-built campaign

The failure modes are mundane and all avoidable:

- **No conversion tracking.** A campaign optimising toward conversions
  that are not measured builds fine and learns nothing. Ask the agent to
  verify conversion actions exist before starting.
- **The abandoned tree.** Decline an approval mid-build without saying
  why, end the chat, and you own a campaign shell with no ads. Finish
  the sequence, or ask for a cleanup pass — "list everything created
  this conversation, pause anything incomplete".
- **Approval fatigue.** Six approvals invite skimming, and skimmed
  approvals defeat their purpose. Read the budget call and the final-copy
  call carefully; those two carry the money.
- **Enabling from the chat trigger-happy.** The paused default only
  protects you if the review actually happens. Open the campaign in the
  UI, check it as you would a junior's work, then enable.

## When to build in the UI instead

The honest boundary: use the interface when the work is primarily visual
or exploratory — auditioning image assets, dragging through the
keyword-planner's suggestions, or weighing one bid strategy against
another before you commit. Once you have decided, the connector can make
the switch: it proposes the change, and your AI client asks before it runs if it is set to ask before AdCopilot's write tools. Use the agent when you know
what the campaign should be and want the distance between brief and built
collapsed to one conversation. Most operators converge on brief-driven
builds through chat, with a UI review before enabling — which is the
workflow the [connector setup tutorial](https://adcopilot.cloud/connect-chatgpt-to-google-ads)
gets you to in an afternoon.

## Questions

### Can ChatGPT create Performance Max campaigns too?

Yes, where the connector supports PMax creation — AdCopilot does, including asset groups. The build shape differs from search: instead of ad groups and keywords, the sequence creates brand assets, then the campaign, then asset groups with headlines, descriptions and images — audience signals stay a quick manual add in the UI. The same paused-by-default rule applies, and the same two human decisions — budget and conversion goal — matter more, not less, given how much PMax automates.

### Will the campaign start spending immediately?

Not through a sanely designed connector. Campaigns created via AdCopilot arrive paused — the build completes fully, you review it in the Google Ads interface, and spend begins only when you enable it. That single default converts campaign creation from a risky write into a recoverable draft, and it is worth verifying about any tool before connecting: ask whether created campaigns can go live without an explicit enable.

### Do I need ChatGPT specifically for this?

No — the build runs the same in any MCP client. The same connector address works in Claude, GitHub Copilot, Gemini CLI, Cursor and OpenCode; what varies is how each client displays tool approvals, not what gets built. Use the client you already pay for. ChatGPT users install the AdCopilot plugin from ChatGPT's plugin directory, which the connection guide walks through.

---

This is the markdown copy of https://adcopilot.cloud/questions/can-chatgpt-create-google-ads-campaigns. The index of the site's pages is https://adcopilot.cloud/llms.txt.
