SE Radio 734: Sathiesh Veera on Engineering Data-Protection Guardrails with LLMs

SE Radio 734: Sathiesh Veera on Engineering Data-Protection Guardrails with LLMs

Author: SE-Radio Team August 20, 2026 Duration: 42:32
Sathiesh Veera, a GenAI Solutions Architect at At&T, speaks with host Brijesh Ammanath about the data-protection guardrails required when using LLMs. The core issue is that LLMs sit outside the cloud tenant in most enterprise AI deployments, which means that data leaves the company's perimeter with every prompt, RAG retrieval, and tool call. Contractual agreements can restrict the data that LLM vendors are allowed to use for training and audits, but they don't stop prompt injection or unintended exposure as company data is often shared to LLMs via natural language queries, APIs, tool and function calls, and MCPs. Sathiesh discusses ways to employ security measures and data filtering at each layer to conform to data security policies and protect the data. 

For developers who think deeply about their craft, Software Engineering Radio-The Podcast for Professional Software Developers offers a steady, thoughtful conversation about building software. This isn't about chasing headlines or quick tips; it's a deliberate exploration of the principles, patterns, and hard-won insights that define lasting work in the field. The SE-Radio Team creates each episode as original, standalone content, ensuring you get focused depth rather than recycled conference talks. Every ten days, a new installment arrives, alternating between detailed tutorial-style deep dives on specific technologies or methodologies and candid interviews with influential voices and practitioners from across the industry. Tuning in means joining a continuous learning journey where complex topics are broken down with clarity, from system architecture and language design to team dynamics and career development. This podcast serves as a reliable educational archive, a resource you can return to as your experience grows, always anchored in the realities and challenges faced by professional developers every day.
Author: Language: en-us Episodes: 50

Software Engineering Radio - The Podcast for Professional Software Developers
Podcast Episodes
SE Radio 697: Philip Kiely on Multi-Model AI [not-audio_url] [/not-audio_url]

Duration: 56:33
Philip Kiely, software developer relations lead at Baseten, speaks with host Jeff Doolittle about multi-agent AI, emphasizing how to build AI-native software beyond simple ChatGPT wrappers. Kiely advocates for composing…
SE Radio 696: Flavia Saldanha on Data Engineering for AI [not-audio_url] [/not-audio_url]

Duration: 1:14:25
Flavia Saldanha, a consulting data engineer, joins host Kanchan Shringi to discuss the evolution of data engineering from ETL (extract, transform, load) and data lakes to modern lakehouse architectures enriched with vect…
SE Radio 695: Dave Thomas on Building eBooks Infrastructure [not-audio_url] [/not-audio_url]

Duration: 1:02:49
Dave Thomas, author of The Pragmatic Programmer, The Manifesto for Agile Software Development, Programming Ruby, Agile Web Development with Rails, Programming Elixir, Simplicity, and co-founder of the Pragmatic Bookshelf…
SE Radio 694: Jennings Anderson and Amy Rose on Overture Maps [not-audio_url] [/not-audio_url]

Duration: 1:03:45
Jennings Anderson, a Software Engineer with Meta Platforms, and Amy Rose, the Chief Technology Officer at Overture Maps Foundation, speak with host Gregory M. Kapfhammer about the Overture Maps project, which creates rel…
SE Radio 693: Mark Williamson on AI-Assisted Debugging [not-audio_url] [/not-audio_url]

Duration: 54:12
Mark Williamson, CTO of Undo, joins host Priyanka Raghavan to discuss AI-assisted debugging. The conversation is structured around three main objectives: understanding how AI can serve as a debugging assistant; examining…
SE Radio 692: Sourabh Satish on Prompt Injection [not-audio_url] [/not-audio_url]

Duration: 1:04:36
Sourabh Satish, CTO and co-founder of Pangea, speaks with SE Radio's Brijesh Ammanath about prompt injection. Sourabh begins with the basic concepts underlying prompt injection and the key risks it introduces. From there…
SE Radio 691: Kacper Łukawski on Qdrant Vector Database [not-audio_url] [/not-audio_url]

Duration: 59:51
Kacper Łukawski, a Senior Developer Advocate at Qdrant, speaks with host Gregory M. Kapfhammer about the Qdrant vector database and similarity search engine. After introducing vector databases and the foundational concep…
SE Radio 690: Florian Gilcher on Rust for Safety-Critical Systems [not-audio_url] [/not-audio_url]

Duration: 1:03:44
Florian Gilcher, co-founder of Ferrous Systems and the Rust Foundation, speaks with host Giovanni Asproni about the application of Rust in mission- and safety-critical systems. The discussion starts with a brief overview…
SE Radio 689: Amey Desai on the Model Context Protocol [not-audio_url] [/not-audio_url]

Duration: 58:36
Amey Desai, the Chief Technology Officer at Nexla, speaks with host Sriram Panyam about the Model Context Protocol (MCP) and its role in enabling agentic AI systems. The conversation begins with the fundamental challenge…