For manufacturers: measure Overall Equipment Effectiveness on each machine from a short study, rank the causes of lost time, and put an honest pound value on fixing them.
How productive are the machines?OEE for each: availability, performance, quality.
Where does the time go?Breakdowns, changeovers, waiting, slow running, rejects.
What's it worth?Only where extra output would sell, or hours would be saved.
What do we fix first?The causes, ranked by value, with owners and dates.
Choose this when you make things on machines and want to know how much of their time really produces good output.
Founder pricing. The method, the calculation spreadsheet with 14 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.
The three parts side by side, in a one-page study, with a repeat study to measure the change.
Set up at each machine, then analysed for you.
Lost time counted as money only where it really is.
And a dated plan for the biggest.
See what the ones you have could give.
Guided and done for you: OEE measured every week from your counts and stop log, a machine that slips flagged, and each fix checked against the study. Nothing leaves your business, and no decision changes, without one of your people approving it.
A fictional 45-person injection moulder logged every stop on five presses for four weeks: OEE came out at 67%, with a third of planned time producing nothing saleable.
Valued honestly (lost crates only up to what would sell, lid-press time only up to the overtime it could cut), the losses are worth £71,883 a year, and modest fixes capture £64,972 of it.
Every stop for two to four weeks, with counts.
Availability, performance and quality.
What the losses are honestly worth.
The top causes, with owners and dates.
Each week the agent measures OEE in your own accounts and flags a machine that slips or a fix that is late.
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 through a study.
Book a call