For businesses whose customer and prospect records are spread across a CRM, the accounting package, a mailing tool and spreadsheets: a profile of every source and field from your own exports, duplicates counted by stated rules, records past your retention period, and who you may contact by email, post and phone, a clean-up rulebook with who checks each decision and the hours it takes, entry rules and a 30-minute monthly routine so it stays clean, and the same counts taken again 90 days after the clean-up.
How bad is it?Every source and field profiled from your exports.
What do we do about it?A written rule, a decision and a checker for each problem.
Who may we contact?Retention, basis and permissions under UK GDPR and PECR.
Will it stay clean?Entry rules, a monthly routine, and the same counts after 90 days.
Choose this if your CRM, accounts and mailing lists disagree, hold the same customers twice and people who left years ago, and nobody can say who you may contact. It comes before the Target Account List, Customer Retention Review and Win-Back Plan, which need clean records.
Founder pricing. The method, the calculation spreadsheet with 29 built-in checks, and a complete worked example are built and tested. The first client for this product gets the founder price, in return for permission to measure the results and, if they are good, write them up as a case study. After that, the price goes up. Book a call to take the founder place.
Unlocks: clean records will make the Target Account List, Customer Retention Review, Lapsed Customer Win-Back Plan, Automated Email and Text Flows Plan and Direct Mail Campaign Plan possible; Measure later: the duplicate rate, required fields filled, returned post, UK GDPR basis recorded, customers matched and the share you may lawfully email are recorded now and counted again, the same way, 90 days after the clean-up. Any £ comes only from your own records, such as returned post and duplicate mailings, shown beside the one-off and yearly cost of the clean-up.
A Foundations product: the groundwork the money products depend on. Its value is shown this way rather than as a single headline figure, and every number in it is labelled counted, estimated or assumed.
Completion and invalid formats by source and field, counts only, and duplicates counted by stated rules: same email, same company and postcode, similar names checked on a sample first.
Each problem's rule, decision, who checks and the hours, in working order.
Basis and permission by channel, soft opt-in, TPS and CTPS; ICO guidance cited, not legal advice.
Required fields enforced and a 30-minute check each month.
Six measures counted the same way 90 days after the clean-up.
Guided and done for you: an agent in your own accounts checks each week's new records against your entry and duplicate rules and prepares a fix list for the person who looks after each system. Nothing leaves your business, and no decision changes, without one of your people approving it.
A fictional 46-person plumbing and heating trade supplier held 12,010 records across its CRM, accounting package and mailing tool. 8.7% of the CRM and accounts records were extra copies, only 55% had a UK GDPR basis recorded, 64% of email addresses could lawfully be marketed to, and 318 invoiced customers weren't in the CRM at all.
The clean-up rulebook covers 24 problems: past-retention records purged first, then merges, then the UK GDPR basis, about 320 hours with the allowance. Entry rules and a 30-minute monthly routine stop it coming back. The same counts are taken again on 11 March 2027.
Every source and field, from your exports.
A rule, a decision and a checker per problem.
Entry rules and the monthly routine.
The same counts again after 90 days.
An agent checks each week's new records against the rules.
The same method and the same spreadsheet in every option. You choose how much of your own time goes in.
For owners comfortable with a spreadsheet and an AI assistant.
For owners who want a second pair of eyes on the data and the analysis.
For owners who would rather hand over the data and get the answer.
It is built on the open Agent Skills standard and designed for Claude (any plan, with code execution switched on). A paste-in version is included for ChatGPT, Gemini and Microsoft Copilot; it has not yet been tested on them.
The calculations live in the spreadsheet, not in the AI, so the numbers don't depend on which assistant reads them.
Book a short call to talk it through.
Book a call