Ads

The Ads node pulls your Responsive Search Ad (RSA) creatives directly from Google Ads into an Agent workflow. It returns headlines, descriptions, final URLs, and performance metrics per ad.

Ads node is the creative layer of the Google Ads nodes. Where the other nodes cover which queries triggered your ads (📄 Search Terms), which keywords you bid on (📄 Keywords) and so on, this node focuses on the ad creatives themselves and how they're performing.

Use this node when you need to audit ad copy at scale, identify creatives that need a rewrite, or check whether your messaging aligns with how AI engines currently describe your category.

When to use this node

Use the Ads node for tasks such as:

• RSA creative audits: pull all live headlines and descriptions and evaluate them at scale

• Copy iteration: identify which creatives are underperforming and generate rewrite candidates

• Brand voice scoring: score ad copy against brand guidelines or tone-of-voice rules

• AI search alignment: check whether your ad messaging aligns with how AI engines currently describe your category

• Weekly ad digests: include ad performance alongside search term and keyword data in a single weekly summary for your team

Node configuration

Google Integration (required)

Select a previously connected Google account, or click + Add integration and follow the prompts to connect one. This is a one-time setup. Once you add an integration, it's available in all future sessions until you remove it in Account Settings > Integrations.

Google Ads Account (required)

Select the Google Ads customer account from the dropdown. The picker handles both Manager accounts and sub-account selection.

Campaigns

Select the ad campaigns from the dropdown. To include every active campaign, leave the field empty.

Ad Groups

Select the ad groups from the dropdown. To include every ad group within selected campaigns, leave the field empty. To see the ad group options in the dropdown, select at least one campaign in the Campaigns field.

Date Range (required)

Select the date range to pull ad performance over. Choose from available presets (today, yesterday, last 7 days, and others) or set a custom range.

Output Fields

Select the fields to include in the output. The options include metrics and campaign details, such as Impressions, Clicks, Conversions, Campaign Type, and Bid Strategy Type. To return output unfiltered, leave this field empty.

Output Label

Enter a descriptive label for this step's output, for example ad_data or rsa_performance_last_7_days. The label becomes the variable name you reference in later nodes.

Output

The node outputs your ad data in JSON format, including:

• headlines, descriptions, and final URLs

• performance metrics: impressions, clicks, cost, and others

Pass the output to:

• 📄 Prompt LLM for AI analysis: creative audits, brand voice scoring, copy rewrite suggestions, or AI search trend alignment checks

• 📄 Slack integration to push an automated weekly ad creative digest to your team channel

• Google Sheets (Write Row) node to log ad performance data over time

• Code node or Conditional node to filter, sort, or slice the data (for example, keep only the top 10 creatives by CTR) before passing a clean dataset to the LLM

Example usage: RSA creative audit

Set up an Agent to score every live ad creative against brand guidelines and surface rewrite candidates automatically. Here is the example structure:

1. Ads node

• Select your Google Integration and set Google Ads Account to your Google Ads account

• Set Date Range to Last 7 days

• Set Campaigns, Ad Groups and Output Fields filters as needed

• Set Output label to ad_data

2. Prompt Responses node

• Set Date range to Last 7 days

• Select relevant topics from the Topics dropdown

• After selecting a topic, relevant prompts are selected automatically; edit the selection in the Prompts dropdown

• Set Output label to ai_prompt_responses

3. 📄 Prompt LLM node

• Enter the prompt:

  You are a brand copywriter. Review these datasets:
  - RSA creatives: {{ad_data}}
  - AI prompt response data: {{ai_prompt_responses}}
  
  For each ad, score each headline and description 1–5 against:
  - Brand voice alignment (clear, confident, not generic)
  - Alignment with the language and themes AI engines are actually
  using to describe this category (from {{ai_prompt_responses}})
  
  Flag any headline or description scoring 1–2 as a rewrite candidate.
  
  For each flagged item, write one improved alternative that mirrors
  the language patterns winning in AI answers.

• Set Output label to creative_audit

4. 📄 Slack integration - Slack Message node

• Select the Slack workspace and channel to receive updates

• Input the message text, or use the creative_audit variable in the Message field

Best practices

Scope by campaign and ad group

Pulling all ads data from all campaigns and ad groups at once can return an unmanageably large dataset. Use the built-in campaign and ad group filtering to scope results before passing them to subsequent nodes.

Use 📄 List Campaigns node to discover the active campaign set first, map campaign names to IDs, or fan out the workflow across every campaign dynamically.

Pair with other Google Ads nodes

Pair with 📄 Search Terms to see what users searched, what ad they saw, and how that ad performed.

Pair with 📄 Keywords to see if your highest-bid keywords appear in your RSA headline copy.

Combine with Profound data

Ads node is useful on its own, but it becomes most powerful when combined with Profound data nodes:

• Add a Prompt Responses node to score ad copy against real AI engine language

• Add a ​ 📄 Citation Pages node to check if your landing page (final URL) is already being cited by AI engines

Process the output data

Ads node can return hundreds of rows for larger date ranges. Passing a large dataset directly to a 📄 Prompt LLM node risks hitting token limits and introducing noise from low-volume, irrelevant terms.

A good way to pre-process the data is to use the Agent Assistant: describe what you want done with the data, and let the Assistant select and insert appropriate nodes into your Agent.