# AI Hallucination in PPC: When the Numbers Are Made Up

AI hallucination in PPC has a shape: convincing metrics with no tool call behind them. How grounding changes the equation and verification closes it.

Glossary · Published 2026-08-10.

> AI hallucination is a language model stating something convincing that is not true — in PPC, a metric it never fetched, a setting it misremembered, a report it invented. The tell is a confident number with no tool call behind it. The cure is architectural: connect the model to the account so it must fetch before it asserts, then verify that it did.

AI hallucination is a language model asserting something convincing that is not true. In PPC work it has a specific, recognisable shape: a metric that was never fetched, a setting described from memory of how accounts usually look, a tidy month-on-month comparison for a month the model never saw. The numbers arrive fluent, formatted and wrong — and the tell is always the same: *no tool call behind them*.

The word suggests malfunction, but the mechanism is ordinary. A language model is a prediction engine, not a database; asked for your CTR without access to your account, the only thing it *can* produce is a statistically typical CTR. Confabulation is what filling a gap looks like when the generator is fluent.

## How hallucination happens — and what grounding changes

Ungrounded, the failure modes in ads work are predictable. Invented metrics: ask a disconnected chatbot about your wasted spend and it will discuss convincing wasted spend, sometimes with invented specifics. Misremembered configuration: descriptions of your settings drawn from the average of all accounts rather than yours. Convincing-but-wrong technicalities: [GAQL](https://adcopilot.cloud/glossary/gaql-google-ads-query-language) queries with field names that nearly exist. Each error is fluent enough to survive a skim, which is what makes the class dangerous in a spend context.

Grounding changes the equation structurally. An agent connected to the account through [tool calls](https://adcopilot.cloud/glossary/tool-calling) does not need to imagine your data — it fetches, and the fetch is visible: tool, account, query, result, all shown in the client. For anything actually retrieved, the invented-number problem disappears, because the number has a receipt.

What grounding does not do is finish the job. A connected model can still misread what a tool returned, carry a stale figure forward through a long conversation, or quietly bridge an ungrounded gap with pattern memory. The failure shrinks from "made up" to "mishandled" — a smaller problem, and still a problem.

## The receipts habit that closes the gap

The working discipline is *receipts*: every number that matters should trace to a visible tool call. Clients display each call an agent makes, so the check costs seconds — the metric either has a fetch behind it, with the date range you intended, or it is conversation. This is the same verification habit that applies to changes — trust the log, not the recollection, as argued in [verify what your AI changed](https://adcopilot.cloud/blog/verify-what-your-ai-changed) — extended to reads.

Prompt patterns push in the same direction, and they are simple enough to paste at the top of any working session:

```text
Only report numbers returned by tool calls in this conversation.
State the date range with every metric.
If data is unavailable, say so — do not estimate.
Show which query produced each table.
```

Instructions like these convert the model's default helpfulness — filling gaps smoothly — into the behaviour a spend system needs: flagging gaps loudly. A fuller set of working rules is in the [prompt guidelines for Google Ads AI](https://adcopilot.cloud/tutorials/prompt-guidelines-for-google-ads-ai).

The honest summary: hallucination is why an unconnected chatbot cannot manage an ad account, and grounding-plus-receipts is why a connected agent can. The difference is not a smarter model. It is an architecture in which asserting requires fetching — and a user who glances at the receipts.

## Questions

### Can a connected AI still hallucinate?

Yes — less, and differently. Grounding through tool access removes the invented-number problem for anything the model actually fetched, but it can still misread a result, blur two campaigns in a long conversation, or fill an ungrounded gap from pattern memory. Verification stays in the workflow; connection shrinks the problem, it does not retire it.

### How do I know a number came from my account?

Check the receipts. Your client shows every tool call the agent made — which tool, which account, what came back — so a real number traces to a visible call and query. If a metric appears with no call behind it, treat it as unverified and ask the agent to fetch it. The habit costs seconds and converts trust into inspection.

---

This is the markdown copy of https://adcopilot.cloud/glossary/ai-hallucination-ppc. The index of the site's pages is https://adcopilot.cloud/llms.txt.
