Technically Speaking with Chris Wright

Build a production-ready AI toolbox ft. Cat Weeks

While generative AI demos are flashy, moving those capabilities into a reliable, secure enterprise production environment is a different ballgame. In this episode of Technically Speaking, Red Hat CTO Chris Wright sits down with longtime Red Hatter and engineering leader Cat Weeks to dismantle the myth that you need a massive ""Frontier Model"" for every task. Together, they explore the practical realities of enterprise AI, advocating for a ""right tool for the job"" approach. The conversation dives deep into the necessity of moving away from monolithic models toward a diverse fleet of specialized Small Language Models (SLMs) and agentic workflows. They also tackle the critical ""illities"", reliability, security, and portability, that often derail projects after the proof-of-concept phase. Beyond the code, Chris and Cat discuss the human and process challenges of AI adoption, from navigating employee fear to ensuring data stewardship. Tune in to discover the differences between RAG and fine-tuning, how to manage agent identities, and why the future of enterprise AI belongs to a toolbox of specialized solutions, not just one giant hammer.

Platform engineering for AI agents ft. Tushar Katarki

A decade ago, the shift from monolithic applications to microservices created an explosion of complexity that only Kubernetes could tame. Today, the enterprise is facing a similar inflection point. We are moving beyond simple chatbots to "Agentic AI"—autonomous systems capable of planning, tool calling, and executing complex workflows. But with this innovation comes fragmentation: how do you manage security, memory, observability, and scale across thousands of agents and models? In this episode of Technically Speaking, Red Hat CTO Chris Wright sits down with fellow Red Hatter Tushar Katarki to explore the critical infrastructure needed for the next wave of AI. They discuss why the agentic era needs its own "Kubernetes," the rise of the Model Context Protocol (MCP) for connecting data, and the emerging concept of an "Agent Mesh" to handle identity and security. Tune in to discover how platform engineering can bridge the gap between AI innovation and production stability, enabling enterprises to build scalable, open platforms for the future of automation.

Driving healthcare discoveries with AI ft. Jianying Hu

We often hear about AI's potential to generate text and code, but its application in healthcare and life sciences promises a more profound impact: solving our most fundamental challenges in disease and medicine. This isn't just about applying existing LLMs; it's about building entirely new foundation models that understand the complex language of biology itself. To explore this new frontier, Red Hat CTO Chris Wright speaks with Dr. Jianying Hu, an IBM Fellow, Global Science Leader of AI for Health, and Director of Healthcare and Life Sciences Research at IBM. Dr. Hu shares her extensive insights and expertise on: •  The fundamental shift from general-purpose LLMs to domain-specific AI foundation models that learn the complex, multimodal language of biology. •  How these new models power ""in silico"" simulations to accelerate drug discovery, validate new experiments, and test therapeutic efficacy. •  The critical role of collaboration in applying AI, as seen in the IBM & Cleveland Clinic Discovery Accelerator, to create models that lead to personalized medicine. •  Why open science and shared community benchmarks are essential for driving the next wave of medical breakthroughs. Join in as they explore how this foundational, collaborative work is creating a new paradigm for scientific discovery. And discover why the future of medicine isn't just about a single AI model, but about building an open, iterative ecosystem that combines deep domain expertise with the power of AI to understand biology from the ground up.

Security for the AI supply chain ft. Aeva Black

The software supply chain has always been a critical battleground, but AI introduces an exponential increase in scale and complexity. We are no longer just securing lines of code; we are now responsible for securing the models that generate it. This a new reality that shifts the entire attack surface for distributed IT systems. To explore this new frontier, Red Hat CTO Chris Wright speaks with Æva Black, an open source security and policy expert. Æva Black shares their extensive insights and expertise on: •  The fundamental shift from securing code to securing the data, training processes, and models that make up the AI supply chain. •  New, emerging attack vectors, such as exploiting model quantization, and how they are analogous to hardware threats like Spectre and Meltdown. •  The growing burden of low-quality, AI-generated contributions on open source communities and the risk this poses to project sustainability and security. •  Why the concept of “model provenance” is essential for building trust in AI systems. •  The rising importance of public policy and government funding to protect and sustain open source as the critical digital infrastructure it has become. Listen in as they explore how the foundational principles of open source including transparency, collaboration, and community-driven governance, offer our most promising path forward. And discover why the health and sustainability of open source communities are directly tied to the security of our AI-powered future and what enterprise leaders can do to move from passive consumers to active contributors in this critical ecosystem.

Taming AI agents with observability ft. Bernd Greifeneder

As modern IT systems grow too complex for humans to effectively manage, there's growing interest in turning to autonomous AI agents for operations. While powerful, these agents introduce new challenges around trust, reliability, and control. To explore how to solve for this, Red Hat CTO Chris Wright speaks with Bernd Greifeneder, Founder and CTO of Dynatrace [LINK: https://www.dynatrace.com], a company that has long focused on managing complexity with AI. Bernd Greifeneder shares his industry insights and expertise on: •  The evolution from simple application architectures to massive, ephemeral microservices environments that are beyond human-scale to manage. •  Balancing creative, generative AI with fact-based, causal AI to create a reliable and deterministic foundation for autonomous operations. •  The critical need for high-quality, real-time data to create a "digital twin" of a production environment, enabling true root cause analysis instead of just correlation. •  Why building trust is the biggest challenge for agentic AI and how a "human-in-the-loop" approach is essential before handing over the keys. Tune in for an in-depth discussion on the future of autonomous IT. This conversation is critical for any SRE, developer, or technology leader preparing to manage not just their systems, but the AI agents that will run them.