Software Engineering Radio - the podcast for professional software developers

SE Radio is a weekly podcast for professional software developers. Our goal is to be a lasting educational resource, not a newscast. Since 2006, we've been talking to experts from throughout the software engineering universe about the full range of topics that matter to professional developers. Brought to you by IEEE Computer Society and IEEE Software magazine.

SE Radio 706: Yechezkel "Chez" Rabinovich on Observability Tool Migration Techniques 02/04/2026

SE Radio 705: Murat Erder and Eoin Woods on Continuous Architecture 01/27/2026

SE Radio 704: Sriram Panyam on System Design Interviews 01/21/2026

SE Radio 703: Sahaj Garg on Low Latency AI 01/14/2026

SE Radio 702: Derick Schaefer on Modern CLIs 01/07/2026

SE Radio 701: Max Guernsey, III and Luniel de Beer on Readiness in Software Engineering 12/30/2025

SE Radio 700: Mojtaba Sarooghi on Waiting Rooms for High-Traffic Events 12/23/2025

SE Radio 699: Benjamin Brial on Internal Dev Platforms 12/17/2025

SE Radio 698: Srujana Merugu on How to build an LLM App 12/09/2025

SE Radio 697: Philip Kiely on Multi-Model AI 12/03/2025

SE Radio 696: Flavia Saldanha on Data Engineering for AI 11/25/2025

SE Radio 695: Dave Thomas on Building eBooks Infrastructure 11/19/2025

SE Radio 694: Jennings Anderson and Amy Rose on Overture Maps 11/12/2025

SE Radio 693: Mark Williamson on AI-Assisted Debugging 11/06/2025

SE Radio 692: Sourabh Satish on Prompt Injection 10/28/2025

SE Radio 691: Kacper Łukawski on Qdrant Vector Database 10/22/2025

SE Radio 690: Florian Gilcher on Rust for Safety-Critical Systems 10/14/2025

SE Radio 689: Amey Desai on the Model Context Protocol 10/08/2025

SE Radio 689: Amey Desai on the Model Context Protocol Amey Desai, the Chief Technology Officer at Nexla, speaks with host about the Model Context Protocol (MCP) and its role in enabling agentic AI systems. The conversation begins with the fundamental challenge that led to MCP's creation: the proliferation of "spaghetti code" and custom integrations as developers tried to connect LLMs to various data sources and APIs. Before MCP, engineers were writing extensive scaffolding code using frameworks such as LangChain and Haystack, spending more time on integration challenges than solving actual business problems. Desai illustrates this with concrete examples, such as building GitHub analytics to track engineering team performance. Previously, this required custom code for multiple API calls, error handling, and orchestration. With MCP, these operations can be defined as simple tool calls, allowing the LLM to handle sequencing and error management in a structured, reasonable manner. The episode explores emerging patterns in MCP development, including auction bidding patterns for multi-agent coordination and orchestration strategies. Desai shares detailed examples from Nexla's work, including a PDF processing system that intelligently routes documents to appropriate tools based on content type, and a data labeling system that coordinates multiple specialized agents. The conversation also touches on Google's competing A2A (Agent-to-Agent) protocol, which Desai positions as solving horizontal agent coordination versus MCP's vertical tool integration approach. He expresses skepticism about A2A's reliability in production environments, comparing it to peer-to-peer systems where failure rates compound across distributed components. Desai concludes with practical advice for enterprises and engineers, emphasizing the importance of embracing AI experimentation while focusing on governance and security rather than getting paralyzed by concerns about hallucination. He recommends starting with simple, high-value use cases like automated deployment pipelines and gradually building expertise with MCP-based solutions. Brought to you by and . /episode/index/show/seradio/id/38517015