Systems | Development | Analytics | API | Testing

Did you know you can call a Gemini model directly from a SQL query in BigQuery? In this hands-on codelab, Ayo and Annie do exactly that, and use it to solve a real problem: converting messy, unstructured text into clean, structured data at scale. This is Episode 1 of our multi-part series where we build a fully functional, data-aware AI agent on Google Cloud. *What we cover:* Chapters: Speakers: Ayo Adedeji, Annie Wang Products Mentioned: Gemini, BigQuery.

Your customer service team flags churn risk in a quarterly review. Your product team spots low adoption in a dashboard two weeks later. By the time anyone acts, the customer is already gone. The delay is the real cost of fragmented analytics in software companies. Spotter for Software and Tech surfaces those signals in real time. It connects product usage, sales pipeline, and customer health data so that teams can ask questions like “Which accounts dropped engagement this month and what changed?” This way, they get answers quickly and can act immediately.

*Does your enterprise have governance over teams of AI agents?* This week, Tatyana Mamut, PhD, joins The AI Forecast to talk about why agentic AI needs to be managed like human teams. This conversation goes beyond technology; Tatyana also reflects on leadership and representation in tech, challenging assumptions about opportunity, and exhibiting why diverse ways of thinking are critical in an AI-driven world.

Are you using datasets in Qlik Cloud Analytics yet? Before jumping into building a Data Product, there’s one foundational piece you can’t afford to overlook: the dataset. It’s more than just a data asset—it’s the backbone of everything you create in hashtag#Qlik. I just dropped a new video breaking down what a Qlik dataset really is, why it matters, and how to use it the right way before moving on to more advanced builds.

Cortex Code is not more widely available and ready for bigger tasks with the lates updates. e. This announcement brings four major updates: Cortex Code in Snowsight is now generally available interface; the CLI now supports native Windows environments; Agent Teams make it easier to break large assignments into coordinated parallel work; and new agent skills standardize how Cortex Code helps build on data.

TS Imagine eliminated 6,000 hours of effort in customer inquiry handling while increasing speed by 10 times. Using AI has resulted in a five-fold increase in developer productivity; for example, a data engineer's output increased from three pull requests per two-week cycle to fifteen.