# The Weekly Negative Keyword Sweep With AI

A 10-minute weekly workflow: pull costed search terms with an AI agent, classify them, and add approved negatives — with the exact prompts.

Tutorials · Published 2026-08-10, updated 2026-10-26.

> A weekly negative keyword sweep with an AI agent takes four steps: pull search terms with cost and no conversions from the last 7–14 days, have the agent classify them (irrelevant, competitor, research, fine), judge the shortlist yourself, then approve one add-negatives call per campaign. Ten minutes a week, and it is the highest-value low-risk write in Google Ads — negatives can only stop spend, never start it.

The weekly sweep is how your agent hunts and kills the spend that buys
nothing — four steps: it pulls the search terms that cost money without
converting, classifies them in seconds, you judge the shortlist, then
approve one write per campaign. Ten minutes, once a week, and it
compounds — every blocked term stays blocked. This page is the workflow;
the concepts behind it — match types, negative levels, which patterns to
block — live in
[negative keywords automation](https://adcopilot.cloud/negative-keywords-automation).

## Step 1 — pull and classify

One prompt does the reading and the first pass of judgement:

```text
In account <account>, pull search terms from the last 14 days with at
least one click and zero conversions, ranked by cost. Classify each:
- irrelevant (nothing to do with what we sell)
- competitor (a competitor's brand)
- research (free / how to / tutorial / diy intent)
- plausibly fine (could convert with more time)
Show cost and the matched keyword per term. Recommend which to block and
at what match type — but do not add anything yet.
```

Expect a classified table and a recommendation list. The *matched keyword*
column is the sleeper: when one keyword matched most of the junk, the
finding is not "add twenty negatives", it is "that match type is too
loose" — a better fix upstream.

The "do not add anything yet" line matters. It keeps the read and the
write in separate steps, which is the habit that makes every agent
workflow reviewable — the same evidence-before-action rule the whole
[prompt library](https://adcopilot.cloud/tutorials/prompt-guidelines-for-google-ads-ai) is built
on.

## Step 2 — judge the shortlist

The agent's classification is a draft, not a verdict. Three rules of
thumb while you scan it:

- **Irrelevant terms: block on sight, exact match.** A term that has
  nothing to do with the offer needs no more evidence than its own text
  plus the cost column.
- **Research intent: block the pattern, phrase match.** One "how to"
  term is noise; five is a pattern. Phrase-match negatives on the pattern
  word beat twenty exact negatives on its variations.
- **Competitor terms: decide, don't default.** Sometimes competitor
  searches convert; sometimes they burn. Ask the agent for the 30-day
  cost and conversion history on those terms specifically, and make this
  call once per quarter rather than re-litigating it weekly.

And one restraint: leave "plausibly fine" alone. A sweep that blocks
everything that has not converted *yet* strangles the campaign's ability
to learn. You are removing waste, not variance.

## Step 3 — approve the write

```text
Add the confirmed list as negatives:
- exact match for the one-off irrelevant terms
- phrase match for the pattern terms
to the campaigns where each appeared. Show me the final per-campaign
list, then make the calls.
```

AdCopilot proposes the negatives once per campaign — the account, the campaign, every term and its match type — and your AI client asks before adding them if it is set to ask before AdCopilot's write tools. Read the term list one last time in the
prompt itself, then approve. Negatives added through the connector land at
campaign level, attributed to your own Google sign-in in change history.

This is the write worth granting first when you are new to
[agent-managed accounts](https://adcopilot.cloud/ai-agent-for-google-ads): it cannot increase
spend, it cannot touch ads or budgets, and
it is exactly the job whose manual version — export, pivot, squint,
paste — was tedious enough that most accounts simply never did it weekly.

## Step 4 — log and stop

```text
Summarise this sweep: how many terms reviewed, how many blocked per
campaign at which match types, total 14-day cost of the blocked terms.
```

The last number is the sweep's receipt: the spend those terms accumulated
in a fortnight is roughly what next fortnight would have cost you.
Paste the summary into your notes and stop — the sweep is deliberately a
bounded job, one slot inside the
[20-minute weekly routine](https://adcopilot.cloud/tutorials/weekly-optimization-routine-with-ai)
rather than an open-ended optimisation session.

## The quarterly counter-sweep

Once a quarter, run the sweep in reverse:

```text
In account <account>, review all existing negative keywords. Which are
phrase-match negatives broad enough that they could plausibly block
traffic we want? Which were added for a problem that no longer exists?
```

Over-blocking is the sweep's only failure mode, and it is invisible in
weekly data — blocked queries never appear in any report. Ten minutes a
quarter reviewing the accumulated list keeps years of sweeps from slowly
walling off real demand. Your first-ever sweep should also check the
inverse conflict — negatives colliding with keywords you actively bid on
— which is step five of
[the 30-minute audit](https://adcopilot.cloud/tutorials/your-first-ai-google-ads-audit).

## Run one now

If an account is connected, the whole first sweep fits in the next ten
minutes: paste the Step 1 prompt, judge the table, approve the write, keep
the receipt. If not,
[Start free](https://app.adcopilot.cloud/signup) — connect with
your Google sign-in and make the sweep the first thing the agent does for
you. It is the fastest route from "connected" to "found money".

## Questions

### How often should the sweep run?

Weekly for established accounts — enough data to judge, little enough that junk never compounds. New campaigns deserve a sweep at 48 hours and again at day 7, because fresh keywords match the widest spray of terms in their first days. If a week returns almost nothing, the account is tight; keep the cadence anyway, it costs ten minutes.

### Should negatives be exact or phrase match?

Exact for one-off junk terms — it blocks that term without collateral. Phrase for patterns you never want ('free', 'jobs', 'tutorial'), since it blocks every search containing the phrase. Broad negatives are rarely worth the risk of over-blocking. When unsure, start exact; you can widen a negative later, but traffic blocked by an over-wide one is invisible.

### Can the agent just add negatives automatically every week without me?

Each write is proposed first, and your AI client asks before it runs if it is set to ask before AdCopilot's write tools, so 'automatic' really means 'you approve one prepared call per campaign'. That is the right amount of friction: the agent does the pulling, classifying and arguing, and you spend thirty seconds on the one judgement that matters — whether each blocked term is genuinely traffic you don't want.

---

This is the markdown copy of https://adcopilot.cloud/tutorials/negative-keyword-sweep-with-ai. The index of the site's pages is https://adcopilot.cloud/llms.txt.
