Uploaded December 2025 | Updated September 2026, 2 weeks ago
In this episode of the InfoQ Podcast, Wes Reisz sits down with Karthik Ramgopal and Prince Valluri from LinkedIn to dismantle the common myths about adopting AI in software engineering. They reveal how LinkedIn moved beyond "hermit developers" and siloed scripts to build a unified Platform Engineering approach for multi-agentic systems.
The conversation dives deep into the Model Context Protocol (MCP), the difference between "foreground" (IDE-based) and "background" (asynchronous) agents, and why specifying intent via specs is the future of software delivery. If you are a Software Architect or Engineering Leader, this is your blueprint for secure, compliant, and observable AI at scale.
Timestamps:
00:00 - Intro
02:16 - Moving Beyond Siloed Proof of Concepts
05:18 - Agents as a New Infrastructure Execution Model
06:47 - Structuring Intent with Specs and Sandboxes
12:23 - The "Human-in-the-Loop" Review Process
14:30 - Foreground vs. Background Agents
21:06 - The Role of Model Context Protocol (MCP)
23:33 - Security, Compliance, and Observability
27:32 - Solving Context with RAG and Historical Data
29:44 - Key Advice for Platform Engineers
#PlatformEngineering #AIAgents #SoftwareArchitecture
đź”— Transcript available on InfoQ: bit.ly/4iFRRhe
Subscribe to the Software Architects’ Newsletter for your monthly guide to the essential news and experience from industry peers on emerging patterns and technologies:
infoq.com/software-architects-newsletter
Upcoming Events:
QCon AI New York 2025 (December 16-17, 2025) - SOLD OUT!
ai.qconferences.com
QCon London 2026 (March 16-19, 2026)
QCon London equips senior engineers, architects, and technical leaders with trusted, practical insights to lead the change in software development. Get real-world solutions and leadership strategies from senior software practitioners defining current trends and solving today's toughest software challenges.
qconlondon.com
QCon AI Boston 2026 (June 1-2, 2026)
Learn how real teams are accelerating the entire software lifecycle with AI.
boston.qcon.ai
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 infoq.com/podcasts
- Engineering Culture Podcast by InfoQ infoq.com/podcasts/#engineering_culture
- Generally AI: infoq.com/generally-ai-podcast
Follow InfoQ:
- Mastodon: https://techhub.social/@infoq
- X: https://x.com/InfoQ?from=@
- LinkedIn: linkedin.com/company/infoq
- Facebook: facebook.com/InfoQdotcom#
- Instagram: instagram.com/infoqdotcom/?hl=en
- Youtube: 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 experts.
- Increase your visibility.
- Grow your career.
infoq.com/write-for-infoq
đź”” Subscribe for more expert-level deep dives into software architecture, platform engineering, and the future of enterprise AI.
💬Do you agree that AI agents require a dedicated platform team, or should they be managed by individual developers? Let us know your take in the comments.👇
In this episode of the InfoQ Podcast, Wes Reisz sits down with Karthik Ramgopal and Prince Valluri from LinkedIn to dismantle the common myths about adopting AI in software engineering. They reveal how LinkedIn moved beyond "hermit developers" and siloed scripts to build a unified Platform Engineering approach for multi-agentic systems.
The conversation dives deep into the Model Context Protocol (MCP), the difference between "foreground" (IDE-based) and "background" (asynchronous) agents, and why specifying intent via specs is the future of software delivery. If you are a Software Architect or Engineering Leader, this is your blueprint for secure, compliant, and observable AI at scale.
Timestamps:
00:00 - Intro
02:16 - Moving Beyond Siloed Proof of Concepts
05:18 - Agents as a New Infrastructure Execution Model
06:47 - Structuring Intent with Specs and Sandboxes
12:23 - The "Human-in-the-Loop" Review Process
14:30 - Foreground vs. Background Agents
21:06 - The Role of Model Context Protocol (MCP)
23:33 - Security, Compliance, and Observability
27:32 - Solving Context with RAG and Historical Data
29:44 - Key Advice for Platform Engineers
#PlatformEngineering #AIAgents #SoftwareArchitecture
đź”— Transcript available on InfoQ: bit.ly/4iFRRhe
Subscribe to the Software Architects’ Newsletter for your monthly guide to the essential news and experience from industry peers on emerging patterns and technologies:
infoq.com/software-architects-newsletter
Upcoming Events:
QCon AI New York 2025 (December 16-17, 2025) - SOLD OUT!
ai.qconferences.com
QCon London 2026 (March 16-19, 2026)
QCon London equips senior engineers, architects, and technical leaders with trusted, practical insights to lead the change in software development. Get real-world solutions and leadership strategies from senior software practitioners defining current trends and solving today's toughest software challenges.
qconlondon.com
QCon AI Boston 2026 (June 1-2, 2026)
Learn how real teams are accelerating the entire software lifecycle with AI.
boston.qcon.ai
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 infoq.com/podcasts
- Engineering Culture Podcast by InfoQ infoq.com/podcasts/#engineering_culture
- Generally AI: infoq.com/generally-ai-podcast
Follow InfoQ:
- Mastodon: https://techhub.social/@infoq
- X: https://x.com/InfoQ?from=@
- LinkedIn: linkedin.com/company/infoq
- Facebook: facebook.com/InfoQdotcom#
- Instagram: instagram.com/infoqdotcom/?hl=en
- Youtube: 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 experts.
- Increase your visibility.
- Grow your career.
infoq.com/write-for-infoq
đź”” Subscribe for more expert-level deep dives into software architecture, platform engineering, and the future of enterprise AI.
💬Do you agree that AI agents require a dedicated platform team, or should they be managed by individual developers? Let us know your take in the comments.👇
