Skip to content

The negative keywords hiding in your search terms.

Ask in Slack and Patricia mines your Google Ads search-terms report: the word patterns burning budget with no conversions, the exact negatives to add and where, and the converters stuck on broad match worth their own bids. She drafts it, you approve it, nothing changes until you do.

What comes back in #marketing when the spend creeps up without the conversions:

#marketingThreadProduct preview
Ricardo GhekiereJust now

@Pati our Google Ads spend crept up last month but conversions were flat. Where is it leaking?

PatriciaAppJust now

Mined the last 30 days of search terms. Three patterns are burning budget with nothing to show for it:

  • 'free' turned up in 41 queries, $310 spent, 0 conversions. Ready to add as a campaign negative.
  • 'jobs' and 'salary' queries, $140 spent, all job-seekers, not buyers. Shared-list negatives ready.
  • 'barrier repair serum' is converting on broad match. Worth breaking out to its own exact-match ad group.
Pulled fromGoogle Ads
Thibaut HennauJust now

@Pati add the negatives and draft the exact-match breakout.

PatriciaAppJust now

Queued for your ok: two negative patterns (one campaign level, one shared list) and a draft exact-match ad group for 'barrier repair serum'. I left the 'barrier repair' research queries alone, they look like early-funnel, not waste. Nothing goes live until you approve. Want me to run this sweep every Monday?

How teams do this today.

Everyone knows the search-terms report needs a weekly clean. It is also the job that never gets done.

The report nobody opens

The search-terms report sits behind three clicks in Google Ads. Cleaning it is nobody's named job, so it gets a look once a quarter, if that.

The budget that leaks quietly

Broad match keeps matching queries you never meant to bid on. The spend adds up a few dollars at a time, so it never trips an alarm, it just lowers the return.

The negatives added by gut feel

When someone does look, they block a handful of obvious terms and miss the patterns spread across hundreds of low-spend queries, which is where the real waste hides.

What it looks like when she owns it.

The Search Terms Miner skill in Patricia's skills catalog, ready to install, with its description and example prompts
Ask her for the skill in Slack and she installs it herself, or add it with one click from her catalog in the app.
A scheduled weekly search-terms sweep task in Patricia, running every Monday, with recent runs showing the negatives proposed and spend saved each week
Set the weekly sweep once and she runs the hygiene job that never gets done, proposing the negatives and flagging the breakouts every Monday.
A search-terms cleanup report drafted by Patricia: the wasted spend found, the negatives added by level, and the exact-match breakouts, ready to present
She turns the sweep into a report you can present: the spend recovered, the negatives added, and the winners promoted to their own bids.

Setup

Running in minutes, then it's hers.

Step 1

Add Patricia to Slack

She joins your workspace like any teammate. Two minutes, no engineering.

Step 2

Install the Search Terms Miner skill

Ask her for it in Slack and she installs it herself, or add it with one click from her catalog in the app. It brings the mining method with it.

Step 3

Connect your Google Ads account

One read-only connection to the account you want cleaned. She reads the search-terms report, she never changes a thing until you approve.

Step 4

Approve the negatives, keep the sweep

She returns the negatives with the spend each one burned and the breakouts worth their own bids. Approve the list, and she runs the sweep on schedule so the report never goes stale again.

What she takes off your plate.

Real behavior of the skill, not a feature list.

Every query, with the money attached

She pulls the search-terms report with spend, clicks and conversions on every query, so the conversation starts from real account data, not a hunch.

Patterns, not one-off bad queries

One, two and three-word analysis finds the word patterns that pile up spend across hundreds of different queries, which is where most of the waste actually hides.

The burned spend as proof

Every proposed negative shows the total spend that pattern cost with nothing to show for it, so the block is evidence-backed, never a guess.

Negatives at the right level

She proposes each negative at the level it belongs, campaign, ad group, or shared list, so the block lands where it should and not everywhere.

Winners promoted, not just losers blocked

Converting queries still served on broad match are surfaced as exact-match breakouts, so the same sweep that cuts waste also sharpens what already works.

Intent judged before anything is blocked

A zero-conversion pattern that looks like early-funnel research is flagged to watch, not to block, so you never cut off demand that converts later. Brand and navigational terms are never blocked without a warning.

Read-only until you approve

Nothing changes in the account until you say yes. She drafts the list, you approve, and only then do the negatives apply.

Things to ask her on day one.

@Pati

Install the Search Terms Miner skill

@Pati

Mine the last 30 days of search terms and show me negatives to add

@Pati

Our spend crept up without conversions, find where it is leaking

@Pati

Which search terms are burning budget with no conversions?

@Pati

Find converting queries stuck on broad match to break out to exact

@Pati

Run the search-terms cleanup every Monday and post what you would change

@Pati

Export the negative keyword list to a sheet

FAQ

Search terms & negatives, answered.

Does Patricia change my Google Ads account on her own?

No. Mining the search-terms report is read-only, and every negative is drafted for your approval first. Nothing applies to the account until you say yes, and she never blocks brand or navigational terms without flagging it.

How is this different from Google's recommendations?

Google surfaces one-off suggestions. Patricia mines the word patterns spread across hundreds of low-spend queries, shows the total spend each pattern burned, and proposes the block at the right level, campaign, ad group, or shared list, in the Slack channel where the decision gets made.

Will she block searches that convert later?

She judges intent before recommending anything. A zero-conversion pattern that looks like early-funnel research is flagged to watch rather than block, so you protect demand that converts down the line.

What do we need to set up?

Add Patricia to Slack, ask her for the Search Terms Miner skill, and connect the Google Ads account you want cleaned. The first mined list comes back in the same thread, with the spend each negative would save.

Can she keep doing this without me asking?

Yes. Set the weekly sweep and she runs the search-terms cleanup on schedule, posting the negatives she would add and the breakouts worth their own bids, still waiting for your approval before anything changes.

Is this all Patricia does?

No. Search-terms cleanup is one skill. The same teammate maps your organic keywords, paces the budget, watches competitor ads, and handles the rest of the work teams hand her, all in the same Slack.

One of the jobs teams hand her. See more campaigns use cases or browse them all.

Everybody deserves a Patricia.

She handles the work your team never gets to. You build the company. See what changes in your first week.

Pick a time that works for you. You get a live walkthrough of Patricia on your real work, and every question answered.

No credit card.