As of 13 August 2026, AI can only partly create a Looker Studio report for your UK business.

What to actually do

1. Hand it to a person

   The route this page recommends

   A person who owns the outcome does this end to end, worth it when the failure is dear.

2. Use a tool built for this

   Second choice

3. Do it yourself

   The distant third

   A chat interface, power-user skill, and roughly 1 hour until you can act on the result.

   How to actually do it

   1. Open the source spreadsheet or export and make an anonymised field list, including field names, data types, date fields, unique keys and a few representative rows.
   2. Write down the approved definition of each KPI, its source column or columns, the comparison period and any exclusions, then paste these details into the prompt.
   3. Paste the prompt and the business details into a chatbot, and save the returned page plan, chart specification, calculated fields and unresolved questions.
   4. Open Looker Studio, connect the approved data source, and follow the returned build sequence while keeping personal data out of the report unless it is necessary and authorised.
   5. Create each page and chart from the specification, then compare every calculated field with the source columns and test a small sample by hand.
   6. Change each filter and date range, check totals for duplicated or missing rows, and reconcile the headline KPIs against the source spreadsheet or export.
   7. Ask a colleague who understands the source data to repeat the reconciliation, confirm that the report supports the intended decisions, and approve the sharing permissions before sending the report link.

   Prompt

   Help me design and build a Looker Studio report for a UK business. Use only the information I provide and do not invent metrics, targets, data sources or business rules.
   
   Business type: [business type]
   Report audience: [audience and decisions they need to make]
   Reporting period: [period]
   Data source or sources: [for example Google Sheets, GA4, Search Console, CRM export]
   Available fields and sample rows: [paste a field list and a small anonymised sample]
   Required KPIs: [list each KPI and its exact definition]
   Required breakdowns: [for example channel, product, region, month]
   Required filters: [list filters]
   Targets or comparisons: [paste approved targets or comparison periods]
   Branding requirements: [colours, logo, title and tone]
   Data protection constraints: [state what personal or confidential data must not be included]
   
   Produce:
   1. A page-by-page report plan with the purpose of each page.
   2. A table listing every chart, its dimension, metrics, filters, date range and recommended visual type.
   3. Exact Looker Studio calculated fields, with field names, formulas and a plain-English explanation.
   4. Any required data cleaning, joining or aggregation steps, including warnings about duplicated rows and mismatched keys.
   5. A build sequence for Looker Studio, including which data source and permissions to select at each stage.
   6. A verification checklist that reconciles every KPI to the source data and tests filters, date ranges, nulls, duplicates and totals.
   7. A short list of unresolved assumptions and questions that I must answer before publishing.
   
   Do not claim that you connected to a source, tested a formula or published a report. Mark anything that needs manual action as MANUAL. Prefer simple, auditable formulas over clever ones.

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.