Delivering AI-powered entertainment that captivates users for hours
CUSTOMER STORY Delivering AI-powered entertainment that captivates users for hours 3 Months To build a proprietary LLM with Databricks 1.5 Million Users Secured in just nine months after launching 12 Hours Of average weekly engagement on Zeta Scatter Lab, a conversational AI startup, is transforming entertainment with their AI-powered B2C platform. With Databricks, Scatter Lab built a large language model (LLM) in just three months, fueling rapid growth — 1.5 million users within nine months, each spending over 12 hours per week on Zeta.
- Agent or tool
- ChatGPT
- Topic
- Customer Support
- Reported on
- Case study (Databricks)
- Added
- 2026-11-11
Why it matters
Support is repetitive and time-sensitive. Agents can draft answers, look things up and handle simple requests, so people can focus on the tricky ones. It is one of 554 sightings filed under Customer Support on Agent Sightings (number 391 by interest), and one of 145 involving ChatGPT.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into ChatGPT or any similar agent and adjust the details to your situation.
I want an agent to handle routine customer questions end to end, and pass anything unclear to a person. The tool in the source case was ChatGPT.
Tip: Start small: run it once on a low-stakes example, read what the agent did, and only then let it run on real work.
Source
Read the original first-hand account on Case study (Databricks): https://databricks.com/customers/scatter-lab. Our summary is a paraphrase; details are in the source.
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.