Analyze Google Ads account  for time-of-day and day-of-week performance differences in clicks and conversions. Identify top-performing hours and days based on CTR and conversion rate, and highlight inefficient windows where spend is less effective. Recommend ad scheduling strategies and pinpoint campaigns that show clear engagement peaks for schedule-based optimization. Instructions: Use only validated platform data, disclose any missing metrics, chunk large sets for aggregation, and base all insights and recommendations on direct data and logic. Provide a prioritized summary and action steps for improvement.

Do a complete Google Ads account analysis for account ID. Focus on:

• Campaign performance by location – country, state, or region breakdown of spends, CTR, and conversions.
  
  
• Identify best and worst-performing locations and flag any exceptional campaign performance in specific areas.
  
  
• Include device-level performance analysis showing where spend and results are concentrated (desktop, mobile, tablet).
  
  
• Evaluate hour-of-day performance to detect strong or poor time windows, and determine if ad scheduling can improve results.
  
  

Instructions for all analyses:

• Validate data directly from Google Ads; do not use sample or hypothetical numbers.
  
  
• Disclose any metrics missing or unavailable due to system limitations.
  
  
• Process large datasets in chunks for accurate aggregation.
  
  
• Ensure every recommendation is supported by performance data and logical reasoning.
  
  
• Conclude with a prioritized summary of findings, action steps, and expected improvements.

Analyze Google Ads account data for drastic changes in keyword-level spends within campaigns over the last 30 days, compared to the previous 30-day period. Identify keywords with large increases or decreases in spend, and for top performing campaigns/adgroups, also check for drastic changes in keyword-level conversions. For each keyword with significant shifts, report monthly spend and results for “top last month” vs “top this month,” including bottom-performing keywords for both periods. Clearly show comparison tables for all metrics available (spend, impressions, clicks, conversions, CPC, CPL, etc.). Validate all data points directly from the platform. Disclose and explain any unavailable metrics or missing data due to system limitations. If data sets are too large, chunk the analysis and aggregate for final reporting. Support every finding and hypothesis with direct data and clear logic. Conclude the analysis with a concise prioritized summary of main findings and actionable next steps to improve keyword performance and account results.

Analyze Google Ads data to identify all campaigns experiencing impression share loss, indicating whether loss is primarily due to ad rank or budget constraints. Present a clear table for each campaign showing:

• Total Impression Share
  
  
• Impression Share Lost (Rank/Budget)
  
  
• Root Cause
  
  
• Actionable Fixes (bid increase, ad quality, or budget changes)
  
  

For each campaign, also provide keyword-level and landing-page metrics for top and bottom performing keywords based on conversion performance, focusing on Keyword Ad Rank, impressions, clicks, conversions, and conversion rate.

Highlight keywords or landing pages with strong or poor performance and provide precise, actionable recommendations to improve impression share and conversion results.
Report any unavailable metrics or data limitations, and if large data sets exist, process them in chunks before aggregation.

General Instructions:

• All numbers validated from Google Ads—no speculation or fabricated data.
  
  
• Disclose incomplete metrics clearly.
  
  
• All insights supported with specific metrics and logical reasoning.
  
  
• End with an executive summary of root causes and prioritized next steps for higher performance.

Review Google Ads account data to identify any campaigns with drastic changes in CTR (Click-Through Rate) over the selected period. If no campaign shows significant CTR shifts, analyze top performing campaigns for adgroups with sharp CTR fluctuations. For all identified campaigns/adgroups, show CTR percentage change, associated impressions/clicks, and relevant date range. Next, list the ad headlines with the highest CTR in the account and recommend the top 2-3 headlines for implementation in low-CTR adgroups to improve performance. Additionally, provide detailed CTR analysis at the keyword and ad level, identifying both the best and worst performers, and highlight actionable recommendations with supporting data. Disclose any missing or partial data and, for large data sets, process in manageable chunks and aggregate at the end. Finish with a concise summary of drivers behind the CTR changes and prioritized, data-backed next steps for improvement.

General Instructions:

• Validate all figures directly from the Google Ads dataset.
  
  
• Clearly disclose metrics or dimensions that are unavailable or incomplete.
  
  
• For large data blocks, aggregate for clarity.
  
  
• Support all insights and recommendations with specific metrics and logic.
  
  
• End with an executive summary and prioritized next actions for improvement.

For every campaign using TCPA (Target Cost per Acquisition) bidding, compare the set TCPA to actual CPA from Google Ads performance. Highlight discrepancies, giving exact TCPA, actual CPA, and percentage variance for each campaign. Analyze reasons for over/under-performance (e.g., budget limits, conversion quality, targeting changes) using only validated campaign data. If data is missing or incomplete, state the limitation. End with actionable suggestions to increase or decrease TCPA settings to optimize results, with supporting rationale.

Instructions:

• Always validate all numbers directly from Google Ads data before presenting.
  
  
• Never use sample, simulated, or hypothetical data.
  
  
• Disclose and explain any metrics or data points that are unavailable or limited because of system constraints.
  
  
• If data sets are large, process them in chunks and aggregate results for clarity and completeness.
  
  
• For each insight or recommended action, provide supporting data points and clear logic.
  
  
• Finish every report with a concise, prioritized summary and next steps to improve account performance.

Identify all campaigns in Google Ads with zero or drastically reduced spend in the selected period, reporting the percentage decrease and comparing to prior trends. For each, document reasons where visible in the data (paused status, budget change, eligibility issues, others) and highlight all relevant metrics. Note any missing data and explain limitations. Present a prioritized summary with root causes and steps to reactivate or reallocate spend as appropriate for account growth.

Review all campaigns and keywords in Google Ads for any drastic increase in CPM (Cost Per Thousand Impressions) over the chosen time frame. For each case detected, display the CPM change percentage, impacted periods, and related performance metrics (impressions, clicks, conversions). Clearly explain possible drivers of CPM increases (e.g., auction pressure, targeting shifts, creative fatigue) with supporting data only. Disclose any data retrieval issues. End with concise recommendations to diagnose, monitor, or reduce CPM increases based on findings. Also, add auction insights and quality score reports within the existing report to make it more cohesive.

Analyze Google Ads account data for any drastic changes in campaign spends during the selected period. If no campaigns show drastic spend changes, check for adgroups with sharp spend fluctuations inside top-performing campaigns. For each identified campaign or adgroup, provide the percentage change, highlight the specific dates and metrics affected, and explain the likely reasons for these changes using only validated data. Flag any gaps or unavailable data. Conclude with a concise summary of the root cause and next-step recommendations for spend stabilization or optimization.

Instructions:

• Always validate all numbers directly from Google Ads data before presenting.
  
  
• Never use sample, simulated, or hypothetical data.
  
  
• Disclose and explain any metrics or data points unavailable or limited because of system constraints.
  
  
• If data sets are large, process them in chunks and aggregate results for clarity and completeness.
  
  
• For each insight or recommended action, provide supporting data points and clear logic.
  
  
• Finish every report with a concise, prioritized summary and next steps to improve account performance.

Generate a report using Google Ads data, the report should be for the month of September 2025 and the goal is to uncover top-performing countries, then drill down into state or county level to find both high-performing and underperforming geographies. Clearly indicate which locations drive the best results (CTR, conversions, CPL, ROAS) and which waste budget. For each geography, give detailed data, flag data gaps or retrieval issues, and explain the rationale for suggesting scale-up or exclusion. End with an actionable summary of where to increase investment and where to cut back, supporting each point with data.

Instructions:

• Always validate data directly from Google Ads before presenting.
  
  
• Never use hypothetical or sample data.
  
  
• Disclose and explain any metrics or data points missing due to system limitations.
  
  
• For large data sets, chunk the analysis and aggregate at the end for efficiency and completeness.
  
  
• Each insight or recommendation must be supported by specific data points and a logical explanation.
  
  
• Conclude each report with a clear, prioritized summary and next steps for improving results.

Analyze Google Ads search term data to identify high-potential search terms for addition as keywords, as well as search terms to be excluded. Highlight for the selected time frame which search terms delivered strong conversions and low CPL and which produced wasted spend or poor results. If search term data is too large, process in batches. Offer clear recommendations for inclusion and exclusion of search terms, and finish with a concise summary of actions and expected impact, explaining all logic and findings with supporting data points."

Instructions:

• Validate all data directly from Google Ads before presenting.
  
  
• Do not use hypothetical or sample data.
  
  
• Flag and explain any missing metrics.
  
  
• Chunk large datasets and aggregate findings for completeness.
  
  
• Recommendations must be supported by specific data points and logical explanations.
  
  
• Close with a prioritized summary and next steps for optimization.

Using Google Ads data, produce a keyword performance report for the user-defined time range. Rank and summarize best and worst performing keywords on key metrics (impressions, clicks, conversions, spend, CPL, ROAS) and compare results against the previous same-length period. Document all relevant data points and explain any changes in keyword effectiveness. If any keyword data is incomplete, flag the gap. Offer a final summary with recommendations for keyword optimization, including pausing or bidding changes.

Instruction to generate report:

• Always validate data directly from Google Ads before presenting.
  
  
• Never use hypothetical or sample data in any output.
  
  
• Disclose and explain any metrics or data points missing due to system limitations.
  
  
• For large data sets, chunk the analysis and aggregate at the end for efficiency and completeness.
  
  
• Each insight or recommendation must be supported by specific data points and a logical explanation.
  
  
• Conclude each report with a clear, prioritized summary and next steps for improving results.

Analyze Google Ads data to generate a weekly campaign performance comparison, showing improvement or decline week over week. For each campaign, identify the main metrics (spend, clicks, CPC, CTR, conversions, CPL, ROAS) that led to the change. Explain underlying causes for shifts in performance, referencing only data that is valid and available. If any campaign data cannot be retrieved, clearly note the limitation. If the data is too large, split and process in chunks, then aggregate the results. End with a data-driven summary and actionable recommendations for the next week.

Instructions to generate the report:

• Always validate data directly from Google Ads before presenting.
• Never use hypothetical or sample data in any output.
• Disclose and explain any metrics or data points missing due to system limitations.
• For large data sets, chunk the analysis and aggregate at the end for efficiency and completeness.
• Each insight or recommendation must be supported by specific data points and a logical explanation.
• Conclude each report with a clear, prioritized summary and next steps for improving results.