AI 2 October 2026 2 MIN

“I Want Realism in My AI Agent” | Dom Orsini, Fivetran @BDL

“My AI is very confident, very agreeable, and it doesn’t challenge me enough.”

In this interview, Shubhangi Dua, Podcast Host, Producer and B2B Tech Journalist at EM360Tech, speaks to Dom Orsini, Principal Customer Solution Architect at Fivetran, at Big Data LDN 2026 at Kensington Olympia, London. 

Last year, agentic AI was the talk of the town at BDL; this year, Orsini tells Dua that we’re seeing agentic AI paired with context. “While people have tried to achieve something with AI, a lot has failed, but the models have got exponentially better.”

What’s happened is that the current tech stack was designed for human use, but it is rapidly shifting to be built for AI agents.

Enterprises are now committing to specific proprietary formats, vendor tools, or specific compute engines when they don't need to.

“I’ve been working in data integration for 15 years, and the only constant is change. Nobody here knows what’s going to happen next year. Enterprises are trying to understand, but it’s moving faster than ever. It’s still very sandboxed,” he tells Dua. 

Dua asks Orsini if he could attribute a human trait to his personal AI agent, what would it be and why. He says, “I want my AI agent to be more realistic.”

“My AI is very confident, very agreeable, and it doesn’t challenge me enough,” the Fivetran Solution Architect states. 

Visit Fivetran.com.

Fivetran + dbt Labs deliver the data infrastructure layer that makes agents trustworthy — from the moment data moves, through every transformation, to the context an agent reasons from.

The Fivetran platform moves, manages, and transforms data from every system a business runs on into a secure, reliable foundation engineered to evolve, with the flexibility to work across clouds, engines, and tools. With Fivetran, analytics, operations, and AI run on data you trust and control. Thousands of organizations worldwide, including OpenAI, LVMH, Pfizer, and Verizon, rely on Fivetran to turn data into a competitive advantage.

Learn more at Fivetran.com, or follow Fivetran on LinkedIn.

Since 2016, dbt Labs has been on a mission to help data practitioners create and disseminate organizational knowledge. dbt is the standard for AI-ready structured data. Powered by the dbt Fusion engine, it unlocks the performance, context, and trust that organizations need to scale analytics in the era of AI. Globally, more than 100,000 data teams use dbt, including those at Siemens, Roche and Condé Nast.

Learn more at getdbt.com, and follow dbt Labs on LinkedIn, X, Instagram, and YouTube.