# How we monitor ad performance

The ad-performance agent we run on Kortix — connected to Google Ads and Meta Ads, with alerts in Slack. Every day it checks budget pacing, CPA and ROAS drift, and underperforming ads and keywords, then posts ranked findings and optimization recommendations — it never changes a budget, pauses a campaign, or edits an ad itself.

Canonical page: https://openchatly.com/use-cases/ad-performance

Paid ad spend drifts quietly. A campaign paces ahead of budget three days into
the month. A cost-per-acquisition creeps up for a week before anyone notices
the trend line. A keyword that used to convert keeps taking budget from ones
that still do. None of it is a single dramatic failure — it's a slow leak
across two ad platforms that nobody has time to check line by line every
morning.

We run an ad-performance agent on Kortix that reads campaign spend and
performance from Google Ads and Meta Ads every day and posts ranked findings
and optimization recommendations to Slack. It never touches a budget, a
campaign, or an ad — it only ever recommends.

- **Team:** Kortix
- **Runs on:** Daily cron
- **Connected systems:** Google Ads · Meta Ads · Slack
- **Mode:** Read-only · recommend-only · one Slack post per day

## The problem

Budget pacing, CPA/ROAS drift, and underperforming ads or keywords are each
easy to catch on their own — if someone is looking. In practice they live
split across two platforms with different dashboards, and checking both every
day for every active campaign doesn't survive contact with a real workload. By
the time a weekly review catches a campaign that's overspent its monthly
budget by day ten, or a keyword whose CPA has doubled, the money is already
spent.

The usual fixes don't hold up. Each platform's native alerting fires on its
own thresholds and only sees its own account. A weekly spreadsheet review is
thorough but a week is a long time for a pacing problem or a CPA spike to
compound. And automated bid/budget tools that act on their own remove the one
thing a marketing team actually wants to keep: the decision.

## What we built

On Kortix, a daily cron spawns a fresh agent session. It reads campaign spend
and performance from Google Ads and Meta Ads, checks budget pacing against
each campaign's monthly target, computes CPA and ROAS drift against trailing
performance, flags underperforming ads and keywords and any spend or
click-through anomalies, and drafts prioritized optimization recommendations —
pause a specific ad, shift budget toward a better performer, add a negative
keyword — before posting the ranked list to Slack. It writes nothing back to
either ad platform.

## How it works

### Copy the setup prompt into a new session

Open your Kortix workspace, start a new session, paste this prompt and send it.
The agent writes the agent file, the ad-performance-review skill and the daily
trigger, and opens a change request for you to review. Prefer clicks? Choose
**Use this template** instead.

**Setup prompt**

```
Set up a daily ad-performance agent in this workspace.

1. Create the agent agents/ad-performance.md. Its job is to review Google Ads and Meta Ads spend and post ranked recommendations. It may use the Google Ads, Meta Ads and Slack connectors, and it only reads the two ad platforms.

2. Create the skill skills/ad-performance-review/SKILL.md with these rules:
   - A campaign is overpacing when spend-to-date is more than 15% ahead of linear pace, and underpacing when it is more than 20% behind.
   - Flag CPA up more than 15% or ROAS down more than 15% against the 30-day baseline. Rank campaigns with both first.
   - Flag a search term with 3 or more clicks and no conversions over 14 days as a negative-keyword candidate.
   - Give every finding one concrete action: pause an ad, shift budget, or add a negative keyword. Never change a budget, pause a campaign or edit an ad.
   - Post one ranked list to #marketing per run, with the numbers behind each finding.

3. Add a cron trigger daily-ad-performance-scan to kortix.yaml. It runs the ad-performance agent every day at 07:00 UTC with the prompt "Load the ad-performance-review skill and run one complete ad-performance scan."

4. Tell me which of these connectors are not connected yet.

5. Open a change request with all of it. Do not merge it.
```

### Connect your tools

Open **Connectors** in your workspace and connect Google Ads, Meta Ads and Slack.
Credentials are brokered server-side and never enter the
agent's machine.

- **Google Ads** (Required):
Reads campaign spend and performance, read-only.
- **Slack** (Required):
Posts the ranked list of optimization recommendations.

### Run it once with this prompt

Merge the change request, then start a session with the **ad-performance**
agent and send this prompt. Check the findings against your own dashboards
before you let the schedule take over.

**Prompt**

```
Run one ad-performance scan on Google Ads and Meta Ads. Read only.

1. Pull spend, clicks, conversions, CPA and ROAS for every active campaign, ad and keyword, with the 30-day baseline.
2. Check each campaign's budget pacing against its monthly target.
3. Flag CPA or ROAS drift of more than 15% against baseline, low-CTR ads, and keywords that spend without converting.
4. Draft one recommended action per finding. Do not change anything in either platform.
5. Post the ranked list to #marketing.
```

### Let the daily schedule take over

The change request added this trigger to `kortix.yaml`. From now on the agent
runs every day at 07:00 UTC, each run in a new session on its own cloud computer. To change the time, edit the cron line, or open
**Triggers** in the workspace.

**kortix.yaml**

```yaml
triggers:
  - slug: daily-ad-performance-scan
    name: Daily ad-performance scan
    on:
      cron: "0 0 7 * * *"
    run:
      agent: ad-performance
      prompt: Load the ad-performance-review skill and run one complete ad-performance scan.
```

### Recommend changes, never make them

The agent reads both ad platforms and writes only the Slack post. Every pause,
budget shift and negative keyword is a recommendation. A person on the
marketing team decides and makes the change.

### Read the ranked list

Each run ends with one message in the channel. This is what a run looks like
in the session:

> **Daily ad-performance scan · 07:00**
>
> Prompt: Load the ad-performance-review skill and run one complete ad-performance scan.
>
> Found **7** findings across **12** active campaigns. **1** campaign is
> overpacing and will spend its monthly budget **6 days** early, so the list
> recommends a lower daily budget. **4** search terms spent without a
> conversion in 14 days and are listed as negative-keyword candidates.

> **The pattern**
> A daily **cron** spawns a fresh session with read-only **connectors** into
> Google Ads and Meta Ads. The optimization rules live as a **skill**. The
> agent reads spend and performance from both platforms and writes nothing but
> the Slack post — every pause, budget shift, and keyword change is a
> recommendation, never an action.

## Make it do more

Once it works, paste any of these into the same session.

**Weekly pacing view**

```
Every Monday, post each campaign spend-to-date against its monthly target to #marketing, sorted by the largest gap.
```

**Catch creative fatigue**

```
Flag any ad whose click-through rate fell 7 days in a row, and name the ad in the same ad set to shift its budget to.
```

**Write the change list**

```
For each recommendation, write the exact setting to change in Google Ads or Meta Ads, so a person can apply all of them in one pass.
```

## Guardrails

The agent reads live spend data across two ad platforms, so its access is
scoped and one-directional:

- **Isolation.** Every run happens in its own isolated sandbox. The session is granted access only to Google Ads and Meta Ads, and only the Slack post is written back out.
- **Scoped secrets.** The Google Ads and Meta Ads credentials are encrypted in
  the Secrets Manager and injected into the sandbox at runtime, scoped to the agents you grant them to.
- **Recommend-only.** The agent has no write access to either ad platform. It
  cannot change a budget, pause a campaign, or edit an ad — it can only
  report and suggest.
- **Everything is code.** The agent's optimization rules, thresholds, and
  per-platform permissions are files in the repo, versioned and changed
  through a reviewed **change request** rather than a dashboard setting.

## The outcome

- **Every day:** Spend and performance rechecked across both platforms
- **Recommend-only:** Nothing is ever paused or reallocated automatically
- **2 platforms:** Google Ads and Meta Ads watched in one daily post

The pacing check, the CPA/ROAS trend, and the underperformer scan that used to
require opening two dashboards now arrive as one ranked Slack post every
morning, each finding carrying the numbers and a specific recommendation. The
agent only reads and recommends; the marketing team decides what to pause,
shift, or exclude.
