For owners whose CRM has drifted: the current state counted from one export, then stages for each way you sell with entry and exit criteria, a field dictionary in which every required field serves a report, validation rules, owners and hand-offs, the few automations that matter and UK GDPR and PECR basics, written for whoever configures it, with one page for your team.
What state is the CRM in?Owners, duplicates and completion, counted.
What does each stage mean?Entry and exit criteria, one meaning each.
Which fields, and when?Required only when known and used.
What should it do by itself?Five to ten automations, each owned.
Choose this if your CRM was set up years ago (or a spreadsheet does its job), the stages mean different things to different people and nobody trusts the pipeline report. It comes before the pipeline, win-loss, stalled-deal and tender products, which need its data.
Founder pricing. The method, the calculation spreadsheet with 36 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: from go-live it supplies what the Sales Forecast and Pipeline Review, the Win-Loss Review, Stalled Deal Rescue and Tender Bid Decision ask for in their own kits, such as a stage history, loss reasons, incumbency and bid hours (products that run off the ledger or call logs aren't counted); key-field completion, stage-age compliance and validity are recorded now, read early at 90 days and measured again at six months.
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, stage ages and a blind spot-check.
Entry and exit criteria and a time limit.
Links, defaults, when required in each motion.
Who owns each record, what passes when, and five to ten automations, owned, with no contradictions.
With guided or done for you, from go-live your CRM's records are checked each week against the stage rules you agreed, and you are told about any breaks. Nothing leaves your business, and no decision changes, without one of your people approving it.
36 built-in checks; not legal advice.
A fictional 72-person compressed air sales and service firm had a CRM nobody trusted: 15 stages read differently by different people, renewals and tenders in spreadsheets, and key fields only 53% complete on recent records.
The blueprint gives four sales motions 12 stage names, each with entry and exit criteria, a field dictionary in which every required field serves a report, and 9 automations with owners and no contradictions. A blind spot-check found 7 of 20 records wrong; completion, stage ages (53% within limits now) and validity are read early at 90 days and measured again at six months.
Count the CRM as it is today.
Stages, fields, owners and rules.
Every rule tested in the workbook.
The blueprint and a page for the team.
From go-live the agent checks your CRM each week against the agreed stage rules and flags breaks, so the new way of working holds.
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