← All runbooks
gooseworks-ai / composites-google-search-ads-builder

Google Search Ads Builder

Build a complete Google Search Ads campaign from structured product intake through keyword research, campaign architecture, ad copy, negative keywords, bid recommendations, and import-ready Google Ads Editor files. The runbook emphasi

agent codexmodel gpt-5.5snapshot python312-uveval programmatic11 stepsv1.0.0

Deploy Google Search Ads Builder to your jetty.io

One-click installs this runbook into a collection on your Jetty account. You can run it from the Spot dashboard, schedule it, or pipe inputs in via the API.

The shape of the run

11 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    1. Create /app/results if it does not exist.
    2. Confirm all required inputs are available: product_name, product_url, value_prop, product_category, icp, monthly_budget, conversion_goal, competitor_domains, and geographic_targeting.
    3. If required inputs are missing, write validation_report.json with overall_passed=false, write summary.md naming the missing inputs, and stop.
    4. Create empty working tables for keywords, ad groups, ad copy, negatives, and validation checks.
    mkdir -p /app/results
    
  2. 2
    Step 2

    Intake and Campaign Brief

    Capture the advertiser's business context before researching keywords.

  3. 3
    Step 3

    Deep Keyword Research

    Generate seed keywords in three buckets: problem-aware, solution-aware, and brand or competitor. For each competitor domain, research organic ranking pages, visible ad positioning, comparison pages, alternatives pages, pricing pages, and category list pages. Use fetched pages to

  4. 4
    Step 4

    Keyword Architecture

    Map keywords to funnel stages: top of funnel, middle of funnel, bottom of funnel, competitor, and brand. Classify intent as transactional, commercial, problem-aware, informational, navigational, competitor, or jobs-to-be-done. Estimate competitive density from SERP quality, adver

  5. 5
    Step 5

    Campaign and Ad Group Structure

    Design tightly themed ad groups around intent, funnel stage, and landing page fit. Avoid mixing broad problem queries with high-intent commercial or competitor terms in the same ad group. Recommended launch structure is:

  6. 6
    Step 6

    Ad Copy Generation

    For every ad group, generate three Responsive Search Ads. Each ad group should include 15 headline candidates and 4 description candidates covering value proposition, pain, differentiator, proof, CTA, category fit, and landing page continuity. Keep headlines within Google Ads lim

  7. 7
    Step 7

    Negative Keywords

    Build campaign-level negatives for low-intent, job-seeking, educational, free-only, template-only, support, login, unrelated consumer, and research-only queries. Add category-specific negatives where ambiguous terms could pull irrelevant traffic. Add ad-group-level negatives to p

  8. 8
    Step 8

    Bid Strategy and Budget Recommendation

    Recommend budget allocation by funnel stage and campaign type. Use high-intent exact and phrase campaigns for the highest-confidence spend, competitor campaigns only when landing page and brand strategy support them, and exploratory problem-aware campaigns with capped budgets.

  9. 9
    Step 9

    Export Files

    Create `google_ads_editor_import.csv` with campaign, ad group, keyword, match type, final URL, headline, description, status, bid, budget, and negative keyword rows as appropriate for Google Ads Editor review. Also update the strategy document with campaign overview, research sum

  10. 10
    Step 10

    Validate Outputs

    Run structural checks before finishing:

  11. 11
    Step 11

    Iterate on Errors (max 3 rounds)

    If validation fails, perform up to max 3 rounds of targeted fixes. Re-check the failed files after each round and update `validation_report.json`. Stop early when all required outputs pass validation.