Customer Contact Reasons Analysis
Find out why people contact you and which causes can be removed.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Analyse contact reasons. Sample of ticket subjects or tags with counts: [CONTACT_DATA]. Period: [PERIOD]. Product changes in that period: [PRODUCT_CHANGES]. Cost per contact if known: [COST_PER_CONTACT]. Group contacts into reasons, calculate the share of each as count divided by total, and rank. For the top five, identify whether the cause is confusing information, a product problem, a process failure or a genuine question, and propose a fix that would reduce the contacts. Estimate the effect if a fix removes half of a category, with the arithmetic and cost. Return a table, three quick wins, three larger projects, and a note on data quality problems such as the other tag. Do not claim a cause that the data cannot show. Add a worked mini example: out of 1,000 contacts, 250 were about delivery status, 150 about password resets and 100 about invoices. Shares are 25, 15 and 10 percent. If a status page removes half the delivery status contacts, that saves 125 contacts; at 4 per contact that is 500. Replace with my figures. Add a suggestion for using customer words in titles of help articles so that people find answers before contacting support, and a method to check whether contacts fall after a fix, allowing for seasonal variation. Add a short section on the limits of the data: categories chosen by agents are subjective, volumes reflect who bothers to contact you, and quiet problems may be missed, so supplement with a sample of conversations. Suggest repeating the analysis every quarter and recording the effect of each fix after four weeks, with the contact counts before and after. Include a one-paragraph summary for leadership with the top three causes and the proposed investment. Remind the reader to keep customer details out of the analysis. Close with a rule for revisiting the analysis each quarter and recording the contacts removed by each fix, so the effect of each change is evidence and not assumption.
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.
See an example result (fictional data)
Invented sample of 1,000 contacts. Delivery status 250 (25 percent); password reset 150 (15 percent); invoice query 100 (10 percent); product questions 300 (30 percent); other 200 (20 percent). Proposed fix: a tracking link in the dispatch email. If it removes half the delivery status contacts: saves 125 contacts. At 4 per contact that is 500 a month. Cause check: delivery status is a process gap; password reset is a product issue; invoice queries come from unclear layout. Caveat: the other category is 20 percent, too large to ignore; review a sample of 50.
Illustrative only, made-up data. Your results will differ and must be reviewed.