Twenty days to notice a drop
The business took 20 days to spot a significant drop in the quote funnel. That was only the time to notice it, before anyone began working out the cause.
Around 50 people received a 25-page management information (MI) pack every morning, and nobody read all of it. Ovidius built a system that reads every page, every working day. Before noon, it tells the handful of people who need to act what moved.
Pack in at 11:30, alerts out at 12:00, with nobody involved. The median pack loads in 2.7 min, and 90% load within 3.0 min.
38 working days, four brands, 116 cards sent.
Made by IES in six weeks. Zero developer tickets.
Every in-scope incident with a baseline available.
Four brands made their daily trading, pricing and marketing decisions from one MI workbook. It was rebuilt by hand every morning and emailed to around 50 people. Most readers got five or six pages in. The pack had no way to say which of its 14 metric areas had moved.
The business took 20 days to spot a significant drop in the quote funnel. That was only the time to notice it, before anyone began working out the cause.
Each day was compared with target and with the prior year on its own. The daily swings were wide enough to hide a real trend.
The pack carried no competitor or wider economic context, so a shift in the outside market could look like an internal failure.
Every figure is calculated in a PostgreSQL view, a saved database query. n8n reads the result and decides who needs to know. The language model gets the finished numbers and writes a sentence around them. Each number is calculated in one place only.
n8n checks OneDrive and works out the brand, automatically.
Loaded into 17 mirror tables and flattened by database views. Median time.
14 metrics, as 7, 14 and 30 working-day rolling averages.
Expected-range band plus spike test.
The model writes the narrative, and a check names any number it was not given.
Summary first, then cards to six audiences, at a fixed UK time.
Both tests fire in either direction, so an unusually good movement shows up as readily as a bad one. The spike test adjusts to how much each metric normally moves, so a naturally jumpy metric is not flagged every day.
Schematic. The shapes show how each test fires and are not IES data.
| Expected-range band | Spike test | |
|---|---|---|
| Watches | 7 and 14-day rolling averages | Today's move versus yesterday |
| Fires when | A rolling average sits outside its band | The move is larger than 2.75 standard deviations (SD) over the last 20 working days |
| Catches | Sustained drift | A sharp one-day break the average hides |
| Card reads | “Outside Expected Range” | “Unusual Daily Movement” |
IES sets the band per metric in the Control Centre. The 2.75 SD spike sensitivity is adjustable per metric too.
For a finance audience, a made-up figure is worse than no summary at all. Every field on this card is a database value: latest reading, rolling averages, band limits, the move. The model writes the sentence around them, never the numbers inside them.
A verification step names any figure the model was not given. Commentary on competitors and the wider economy sits in a separate, labelled block, so outside context never mixes with internal figures.
Outside expected range
Within range, evaluated and logged
Unverified figures, declared rather than hidden
The seven-day baseline was 95.1%. The rolling average never left its band, so band-only detection would have reported nothing. The spike test scored the move at z = −11.65, far outside the metric's normal daily movement, and sent the card to the two analysis teams by noon.
Same pattern on 1 July: a second brand's visit-to-web-call at 0.0155 against a 0.0938 baseline, −83.5%, z = −11.51, again inside the band.
IES supplied dates when they knew something had gone wrong, and Ovidius replayed the data for those dates. The rolling bands caught drift well but missed a single-day shock. A system outage on 11 May cut one brand's call-to-sale by 38.1%, while the 7-day average stayed inside its band. So Ovidius added the spike test.
Caught by the band
Caught by the spike test only
Missed with a baseline available
No baseline yet: the incident fell in the first days of data
Outside the 14 contracted metrics
People mute an alerting system that fires every day. The chart shows the share of evaluations that breached each week, from the first two brands through all four.
| Week of | Breach rate | Brands |
|---|
Breach rate across 38 working days
Days with no flag at all, the first on 8 July
Threshold changes made by IES, no tickets raised
Today was the first day we got it to not flag once, which was really good, which is what we've been trying to get to.Commercial Finance · IES Limited
Finance owns what counts as normal. The Control Centre lets IES move a band, preview its impact against recent history, and save it with their name on the change. Drag the sensitivity to see the band respond.
Adjust a metric's threshold band and preview the impact before saving.
Current: band centre 30.7% · sensitivity ±3.9 pp → flags below 26.8% / above 34.6% · tested on the 7-day average · spike 2.75σ
Recreation of the IES Control Centre, using the figures from the breach card in chapter 04.
Alerting since 16 June
breaches surfaced
Alerting since 16 June
breaches surfaced
Joined week of 3 August
breaches surfaced
Joined week of 3 August
breaches surfaced
Figures cover 24 June to 25 August 2026, working days only. Calculations were validated against IES's own source files before handoff. Ovidius measured timings and counts from the alert history. The 20-day figure and the 50-person distribution list come from IES. Brand names are withheld.
Bring the report everyone receives and nobody finishes. In a discovery call we work out which numbers should alert whom, and what it takes to build.
We use Google Analytics cookies to see which pages visitors read, so we can improve the site. Accept to allow them or reject to keep them off. Privacy policy