In this episode of the Data & AI Podcast, host Alex Juarez, Director of Engineering at Mesh-AI, is joined by Elliot Budd (Lead AI Engineer), Millie Wan Marriott (Data Engineer), and Maartens Lourens (Principal AI Engineer) for a deep dive into the rapidly evolving world of AI-assisted coding.

The team explores how AI coding tools have transformed from basic autocomplete suggestions to sophisticated development partners - and what that means for the future of software engineering. From the early days of GitHub Copilot to today's agentic coding systems, they discuss the trust, limitations, and best practices that are shaping how developers work alongside AI.

This episode covers:

• The evolution from autocomplete to agentic coding systems
• Why trust is the critical factor in adopting AI coding tools
• The gap between "vibe coding" and proper engineering practices
• Current limitations: context management, hallucinations, and when AI changes the wrong code
• Emerging best practices and the concept of "guardrail engineering"
• What junior developers need to learn in an AI-assisted world
• The future of verification, testing, and developer satisfaction

Whether you're sceptical about AI coding tools or already using them daily, this conversation offers honest insights into what works, what doesn't, and where the industry is headed.

"Developer satisfaction is at an all-time high with these tools. If five years ago it took you a week to build an API, and now you can do it in an hour - that's really satisfying."

Hosted on Acast. See acast.com/privacy for more information.

In this episode of the Data & AI Podcast, hosts Steve Bryen, CTO at Mesh-AI, and Eric Papaluca, Principal Consultant at Mesh-AI, are joined by Adrian Hornsby, CEO and founder of Resilium Labs, focused at helping customers improve system resilience. Together, they explore what it really takes to build resilient systems and cultures that can adapt, recover, and thrive in the face of disruption.

From the hard lesson of accidentally deleting a production database, to leading Chaos Engineering at Amazon, Adrian shares decades of experience turning incidents into learning opportunities. He explains why resilience isn’t something you buy, it’s something you build, and why cultural foundations are just as critical as technical tools in achieving operational excellence.

This episode dives deep into:

• Chaos vs. resilience engineering - and why the distinction matters
• How game days, postmortems, and psychological safety drive true learning
• The prevention paradox: why good resilience often looks like “nothing happening”
• How AI creates both new opportunities and new risks in incident response
• Why building resilience means transferring knowledge, not just deploying tools

Whether you’re scaling distributed systems, leading incident response, or building a culture of reliability, this is a must-listen for anyone serious about resilience in the age of AI.

“Good resilience is invisible — its output is non-events.” – Adrian Hornsby

Hosted on Acast. See acast.com/privacy for more information.

In this episode of the Data & AI Podcast, host Steve Barrett is joined by Amit Nandi, Solution and Data Architect at Barclays Corporate & Investment Bank.

Amit shares how Barclays migrated its data estate to AWS, built a data mesh to empower quants, and tackled the security and compliance challenges of AI in banking. He also explores the shift from MLOps to AgentOps, the importance of domain expertise, and how to drive real adoption of AI in complex, regulated industries.

Whether you’re modernising data platforms or preparing for the next wave of AI, this is a candid look at the future of operationalising AI in financial services.

Hosted on Acast. See acast.com/privacy for more information.