Context is the Key to the Agentic Architecture Revolution: A Conversation with Baruch Sadogursky

About this episode

Michael Stiefel discusses the role of context in software architecture with Baruch Sadogursky, focusing on agentic AI and context engineering.

In this podcast Michael Stiefel spoke to Baruch Sadogursky about software architecture in the age of agentic AI. Large Language Models can function, albeit stochastically, as reasoning machines capable of interpreting human ambiguity. With the appropriate rigorous context artifacts to control the LLM’s reasoning, software specifications can become the source of truth, while the code becomes a disposable intermediate language. These context artifacts are managed through an engineering discipline, context engineering. Unlike prompt engineering which Sadogursky likened to “voodoo incantations”, context engineering utilizes artifacts such as skills, rules, scripts, feedback, and rigorous evaluation to provide the models with clear intent on what code to write. AI Agents will ask clarifying questions to the architects and clients until the requirements are fully understood. This allows a massive “shift left” to evaluate code quality before it is even written. Testing now validates the accuracy of the specifications. Humans are still responsible for determining the correctness of the requirements by providing the proper context, and validating the final results. Since changes over the…

People in this episode

Host: Michael Stiefel

Guest: Baruch Sadogursky

Topics covered

• software architecture
• agentic AI
• large language models
• context engineering
• microservices
• code quality

Keywords

• agentic AI
• context engineering
• large language models
• software specifications
• microservices
• code quality
• testing

Mentioned in this episode

Organizations: InfoQ

More episodes of The InfoQ Podcast

• From MCP and Vibe Coding to Harness Engineering: How Did AI Native Engineering Evolve in One Year · June 8, 2026 · 41 min
• Requirements Analysis for Architects: A Conversation with Sonya Natanzon · June 1, 2026 · 42 min
• Chasing Efficient Java Development: From 1BRC to Developing Hardwood AI Natively · May 25, 2026 · 41 min
• From Java EE to Quarkus and LLMs: Adam Bien’s Playbook for Boring, Future‑Proof Systems · May 11, 2026 · 37 min
• Roq: Leveraging Quarkus to Build Static Sites at the Speed of Go · May 4, 2026 · 21 min
• A Java Performance Quest: Taming Unsafe Code, Embracing Idiomatic Style & Debugging the Linux Kernel · April 27, 2026 · 41 min