More Podcasts by InfoQ episodes
Published 25 Mar 2026
Duration: 00:54:31
Challenges in operationalizing agentic AI systemsblending microservices, ML, and autonomyinclude security risks, architectural gaps, observability issues, and balancing innovation with ethical, scalable, and sustainable implementation.
Are you ready for your new non-deterministic co-workers? Autonomous agents promise to help build, operate, and run software systems, but they can also...
The podcast explores the challenges of deploying AI in production environments, emphasizing the gap between experimental AI models and their operationalization. It introduces agentic systemsa novel domain blending microservices, traditional machine learning, and autonomous decision-makingwhich present unique complexities such as non-deterministic logic and inter-agent coordination. Examples highlight agentic use cases like autonomous incident response systems and non-agentic ones like deterministic chatbots, underscoring the need for distinct approaches to design and safety. Security risks, including prompt injection, API key leaks, and supply chain vulnerabilities, are prioritized, alongside the necessity for boundary definitions and risk management frameworks to prevent unintended actions in autonomous systems.
Operational and architectural challenges include ensuring observability in dynamic agent workflows, redefining software development lifecycles to accommodate autonomous systems, and balancing innovation with standardization. The discussion also addresses the shift in human roles from passive users to stewards of AI outputs, emphasizing accountability, ethical considerations, and the importance of explainability in complex agent behaviors. Open-source innovation and platform evolution are highlighted as critical for scalability, with a focus on cost efficiency, sustainability, and early experimentation to avoid overreliance on unproven technologies. Future trends point toward tighter AI-hardware integration, cross-organizational agent communication, and a growing need for standardized governance to manage the rapid expansion of agentic systems.
15 Jun 2026 Increasing Users Data Agency: From BlueSky's AT Protocol to the Local-First Software Movement
Discusses challenges in AI integration, the shift to modular cloud-native systems using Apache Parquet, decentralized infrastructures like Blue Skys AT Protocol, the Local First movement prioritizing local data storage, AutoMerge for collaborative non-text files, retrofitting hurdles, and open standards to combat vendor lock-in.
8 Jun 2026 From MCP and Vibe Coding to Harness Engineering: How Did AI Native Engineering Evolve in One Year
The evolving AI adoption in software delivery involves architecture, collaboration, and rapid advancements, highlighting shifts in coding tools from autocomplete to agentic modes, context engineering challenges, hybrid tool use, local model limitations, privacy concerns, and the need for formal validation and industry-academia collaboration to enhance agent autonomy and address reliability gaps.
1 Jun 2026 Requirements Analysis for Architects: A Conversation with Sonya Natanzon
Architects must balance technical and business priorities, prioritize user satisfaction and organizational goals, navigate communication challenges, apply domain-driven design principles, address AI's impact on software development, and adapt to evolving technologies while emphasizing creativity and strategic alignment.
25 May 2026 Chasing Efficient Java Development: From 1BRC to Developing Hardwood AI Natively
AI and architecture challenges, Java's evolving ecosystem with performance optimizations and legacy practices, columnar data formats like Parquet, dependency management, and balancing AI adoption with developer skill retention.
18 May 2026 Context is the Key to the Agentic Architecture Revolution: A Conversation with Baruch Sadogursky
AI adoption in architectural decision-making emphasizes trade-offs between efficiency and complexity, challenges of ambiguous requirements, context-driven engineering, frameworks like the Intent Integrity Kit for iterative clarity, architect roles in managing systems and stakeholder dynamics, and the need to balance AI capabilities with human oversight amid ethical and technical limitations.