Dolezal: GymBeam cut support team from 50 to 3 using Keboola and LLMs
Pavel Dolezal · #2278 How to build a $15M/year AI company. · Sep 3, 2025 · at 42:14
Pavel Dolezal, co-founder of Keboola, explains how client GymBeam used Keboola and ChatGPT to automate customer review moderation.
“What they did, they had a 50, 50, 50 people team. With the support user support, like content support, and their biggest problem, like people give them reviews in 16 languages everywhere, right? One of their biggest issues was that people would, you know, actually spam them, so the competitors would spam their reviews. So they use Kebula, they use, you know, ChangeGPT within their, you know, workflow, Kebula automated that, and so we get the data from reviews, you know, we, you know, like normalizing in Kebula, they, you know, read ChatGPT from Kebula, it, you know, analyzed the data, and then actually wrote the responses, and then again run it through Kebula, and at the end, you know, they would have a human-in-the-loop interface, where people would say yes, no, yes, no, or rewrite. They would go from 50 people down to three people.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →