Trend Detection Without Over-Reading Noise
Separate real change from random variation.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Help me judge whether this change is real. Weekly or monthly values: [DATA_SERIES]. What changed in the business: [BUSINESS_CHANGES]. Decision at stake: [DECISION]. Calculate the average and the typical range (highest minus lowest) of the series before the change. Compare the latest values with that range. Explain in plain words whether the latest values are outside normal variation. Use a moving average of three periods and show it. Return a plain-language verdict: likely real, possibly real, or not distinguishable from noise, with the reasons. List what additional data would settle it and how long to wait. Avoid claiming certainty from a few points. Add a worked example: the first eight values are 52, 48, 50, 55, 47, 51, 49, 53, with an average of 50.6 and a range of 47 to 55. A new value of 56 sits just outside the range, so it is possibly meaningful but could still be noise; two or three consecutive values above 55 would be stronger evidence. Apply the same reasoning to my series. Suggest what else to look at, such as whether something changed in the business at that time, and whether the same movement appears in related metrics.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.