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 course of time will occur, resulting in the regeneration of the code from the specifications, microservices is the best architectural paradigm to use given the current limitations on context windows for LLMs. Orchestration of the services is then done by a human architect to create the application. The architect is also responsible for managing the emergent properties of the system.
Read a transcript of this interview: https://bit.ly/48YWu2n
Newsletter:
Subscribe to the Software Architects’ Newsletter for your monthly guide to the essential news and experience from industry peers on emerging patterns and technologies:
https://www.infoq.com/software-architects-newsletter
InfoQ online certification cohorts:
Online cohorts for senior engineers and architects, built around QCon talks. Join a 5-week confidential peer group to validate your approach and apply practitioner frameworks to the technical challenges you face at work. Learn more: https://certification.qconferences.com/
Upcoming Events:
QCon AI Boston 2026 (June 1-2, 2026)
Learn how real teams are accelerating the entire software lifecycle with AI.
https://boston.qcon.ai
QCon San Francisco 2026 (November 16-20, 2026)
https://qconsf.com/
The InfoQ Podcasts:
Weekly inspiration to drive innovation and build great teams from senior software leaders. Listen to all our podcasts and read interview transcripts:
- The InfoQ Podcast https://www.infoq.com/podcasts/
- Engineering Culture Podcast by InfoQ https://www.infoq.com/podcasts/#engineering_culture
- Generally AI: https://www.infoq.com/generally-ai-podcast/
Follow InfoQ:
- Mastodon: https://techhub.social/@infoq
- X: https://x.com/InfoQ?from=@
- LinkedIn: https://www.linkedin.com/company/infoq/
- Facebook: https://www.facebook.com/InfoQdotcom#
- Instagram: https://www.instagram.com/infoqdotcom/?hl=en
- Youtube: https://www.youtube.com/infoq
- Bluesky: https://bsky.app/profile/infoq.com
Write for InfoQ:
Learn and share the changes and innovations in professional software development.
- Join a community of practitioners.
- Increase your visibility.
- Grow your career.
https://www.infoq.com/write-for-infoq
New Zealand