Session: Game Data For All: How AI Is Democratizing Game Analytics
summary
ClarityQ builds an automated context builder agent that ingests warehouses, BI tools, docs and SQL history to create a semantic catalog of events, tables and company-specific metric SQL so a conversational agent answers analytics queries accurately with an analyst human in the loop. Real examples: AB test root-cause that normally takes days is diagnosed in ten minutes, revealing ad-triggered restarts that drop level completion, and LTV models show second purchase size predicts whales while first purchase >$20 flags mid-value players.
AI-written summary · about
chapters (14)
- 0:00AI in game analytics
- 1:31Traditional analytics pain points
- 3:18GenAI solution structure
- 4:22Raw events and parameters
- 6:27Aggregated tables importance
- 7:29Semantic catalog for metrics
- 8:56Predefined analytical workflows
- 9:59Conversational agents role
- 10:41AB testing analysis example
- 12:51LTV prediction insights
- 14:20Implementation takeaways
- 15:22Onboarding requirements
- 16:04Agent limitations
- 17:08Future of GenAI analytics
related talks
16mGame Data for All: How AI Is Reinventing Game Analytics
32mSponsored Session: Observability and Agentic AI - From Observability to Answers...
47mThomas in't Veld | AI Track | Compass AI & Data Summit 2025
38mAI in action: How to use practically in iGaming beyond the hype?
21mHarnessing Technological Innovation & Accelerating Uptake
45mWhat’s Next in AI for Data and Data Management
43mTesting Agentic AI Applications: Beyond Traditional QA
22mFireside Chat: AI and Data-Driven Sales