Ask HN: What 'AI feature' created negative ROI in production?

5 pointskajolshah_bt2mo ago4 comments

Not demos, real usage. What broke first: data quality, evals, cost/latency, user trust, or support load?”

4 comments

We implemented an AI-powered customer support triage system that initially looked promising in testing. In production, it actually increased our support costs by ~30% because:

The AI would confidently misroute 15-20% of tickets, requiring human review of ALL AI decisions and the Customers lost trust after a few bad experiences and started explicitly requesting human agents also Support agents spent more time correcting AI mistakes than they saved

The breaking point was data quality - our training data was too clean compared to real customer queries. We ended up rolling back to rule-based routing with AI as an optional suggestion tool instead.

kajolshah_btOP2mo ago

This is such a classic failure mode: even a 15–20% confident misroute is brutal because it forces “review everything,” kills trust, and increases repeats/reopens.

When you rolled back, did you keep AI as suggestions only + rules-based routing? And what metric exposed it fastest for you: recontact rate, handle time, or escalation to humans?

Yiin2mo ago

did you generate this reply with chatgpt or do you just naturally like to construct sentences like AI?

1 more reply

j / k navigate · click thread line to collapse