logo
episode-header-image
Yesterday
58m 36s

SE Radio 689: Amey Desai on the Model Co...

se-radio@computer.org
About this episode

Amey Desai, the Chief Technology Officer at Nexla, speaks with host Sriram Panyam 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 IEEE Computer Society and IEEE Software magazine.

Up next
Oct 1
SE Radio 688: Daniel Stenberg on Removing Rust from Curl
Daniel Stenberg, Swedish Internet protocol expert and founder and lead developer of the Curl project, speaks with SE Radio host Gavin Henry about removing Rust from Curl. They discuss why Hyper was removed from curl, why the last five percent of making it a success was difficult, ... Show More
57m 14s
Sep 25
SE Radio 687: Elizabeth Figura on Proton and Wine
Elizabeth Figura, a Wine Developer at CodeWeavers, speaks with SE Radio host Jeremy Jung about the Wine compatibility layer and the Proton distribution. They discuss a wide range of details including system calls, what people run with Wine, how games are built differently, confor ... Show More
52m 17s
Sep 17
SE Radio 686: François Daoust on W3C
François Daoust, W3C staff member and co-chair of the Web Developer Experience Community Group, discusses the origins of the W3C, the browser standardization process, and how it relates to other organizations like TC39, WHATWG, and IETF. This episode covers a lot of ground, inclu ... Show More
1h 2m
Recommended Episodes
Jan 2025
Erik Bernhardsson on Creating Tools That Make AI Feel Effortless
Today on No Priors, Elad chats with Erik Bernhardsson, founder and CEO of Modal Labs, a platform simplifying ML workflows by providing a serverless infrastructure designed to streamline deployment, scaling, and development for AI engineers. Erik talks about his early work on Spot ... Show More
23m 36s
Dec 2016
Ep. 2: Where Deep Learning Goes Next - Bryan Catanzaro, NVIDIA Applied Deep Learning Research
Bryan Catanzaro, vice president for applied deep learning research at NVIDIA, talks about how we know an AI technology is working, the potential for AI-powered speech, and where we’ll see the next deep learning breakthroughs. 
32m 52s
Jun 2024
Generative AI and Hardware Upgrades, Google History and the Dark GPU Theory, Amazon’s Logistics Long Play
A question about generative AI and the hardware powering voice assistants, projecting the GPU future with the dot com bubble as context, and thoughts on Amazon’s capital expenditures and the state of AWS and Amazon Supply Chain. At the end: An Elon hater reviews the Cybertruck. T ... Show More
1h 10m
May 2025
NVIDIA’s Rama Akkiraju on Building the Right AI Infrastructure for Enterprise Success - Ep. 255
Rama Akkiraju, VP of IT for AI and ML at NVIDIA, discusses the transformative power of AI in enterprises. Akkiraju highlights the rapid evolution from perception AI to agentic AI and emphasizes the importance of treating AI as a new layer in the development stack. She also shares ... Show More
34m 52s
Jan 2025
#229 Mitesh Agrawal: Why Lambda Labs’ AI Cloud Is a Game-Changer for Developers
This episode is sponsored by Netsuite by Oracle, the number one cloud financial system, streamlining accounting, financial management, inventory, HR, and more.   NetSuite is offering a one-of-a-kind flexible financing program. Head to  https://netsuite.com/EYEONAI to know more.  ... Show More
56m 7s
Apr 2025
Optimizing For Traditional Search Engines Vs AI Platforms
SEO professionals face a strategic dilemma between traditional search and AI platforms. Chris Andrew, Co-founder and CEO of Scrunch AI, explains why optimizing for both simultaneously is possible by focusing on human-centered content. He reveals how AI models access content in re ... Show More
4m 56s
Apr 2025
AI & SEO Meet Micro-SEO Strategies
Chris Raulf, founder of Boulder SEO Marketing, discusses the integration of AI with micro-SEO strategies. He explains how leveraging artificial intelligence can enhance the precision and effectiveness of SEO tactics, particularly through Boulder SEO Marketing's unique Micro-SEO S ... Show More
25m 38s
Mar 2025
#243 Greg Osuri: Why the Future of AI Depends on Decentralized Cloud Platforms
This episode is sponsored by Indeed. Stop struggling to get your job post seen on other job sites. Indeed's Sponsored Jobs help you stand out and hire fast. With Sponsored Jobs your post jumps to the top of the page for your relevant candidates, so you can reach the people you wa ... Show More
59m 19s
May 2023
TinyML: Bringing machine learning to the edge
When we think about machine learning today we often think in terms of immense scale — large language models that require huge amounts of computational power, for example. But one of the most interesting innovations in machine learning right now is actually happening on a really s ... Show More
45m 45s
Apr 2021
SLP264 Roy Sheinfeld Podcasting 2.0 & Lightning with Breez
Roy Sheinfeld of Breez rejoins me on the show to talk about the latest with Breez and how Lightning Network is enabling a whole new world of possibilities. We chat: Breez updates Merchant adoption of Breez Lightning network podcasting Taking payments offline Cloud backups Lightni ... Show More
1h 4m