Discover how the Model Context Protocol (MCP) is revolutionizing AI systems integration by simplifying complex multi-tool interactions into a scalable, open standard. In this episode, we unpack MCP’s architecture, adoption by industry leaders, and its impact on engineering workflows.

In this episode:

- What MCP is and why it matters for AI/ML engineers and infrastructure teams

- The M×N integration problem and how MCP reduces it to M+N

- Core primitives: Tools, Resources, and Prompts, and their roles in MCP

- Technical deep dive into JSON-RPC 2.0 messaging, transports, and security with OAuth 2.1 + PKCE

- Comparison of MCP with OpenAI Function Calling, LangChain, and custom REST APIs

- Real-world adoption, performance metrics, and engineering trade-offs

- Open challenges including security, authentication, and operational complexity

Key tools & technologies mentioned:

- Model Context Protocol (MCP)

- JSON-RPC 2.0

- OAuth 2.1 with PKCE

- FastMCP Python SDK, MCP TypeScript SDK

- agentgateway by Solo.io

- OpenAI Function Calling

- LangChain

Timestamps:

00:00 — Introduction to MCP and episode overview

02:30 — The M×N integration problem and MCP’s solution

05:15 — Why MCP adoption is accelerating

07:00 — MCP architecture and core primitives explained

10:00 — Head-to-head comparison with alternatives

12:30 — Under the hood: protocol mechanics and transports

15:00 — Real-world impact and usage metrics

17:30 — Challenges and security considerations

19:00 — Closing thoughts and future outlook

Resources:

• "Unlocking Data with Generative AI and RAG" by Keith Bourne - Search for 'Keith Bourne' on Amazon and grab the 2nd edition
• This podcast is brought to you by Memriq.ai - AI consultancy and content studio building tools and resources for AI practitioners.

Unlock the secrets to evaluating Retrieval-Augmented Generation (RAG) pipelines effectively and efficiently with ragas, the open-source framework that’s transforming AI quality assurance. In this episode, we explore how to implement reference-free evaluation, integrate continuous monitoring into your AI workflows, and optimize for production scale — all through the lens of Keith Bourne’s comprehensive Chapter 9.

In this episode:

- Overview of ragas and its reference-free metrics that achieve 95% human agreement on faithfulness scoring

- Implementation patterns and code walkthroughs for integrating ragas with LangChain, LlamaIndex, and CI/CD pipelines

- Production monitoring architecture: sampling, async evaluation, aggregation, and alerting

- Comparison of ragas with other evaluation frameworks like DeepEval and TruLens

- Strategies for cost optimization and asynchronous evaluation at scale

- Advanced features: custom domain-specific metrics with AspectCritic and multi-turn evaluation support

Key tools and technologies mentioned:

- ragas (Retrieval Augmented Generation Assessment System)

- LangChain, LlamaIndex

- LangSmith, LangFuse (observability and evaluation tools)

- OpenAI GPT-4o, GPT-3.5-turbo, Anthropic Claude, Google Gemini, Ollama

- Python datasets library

Timestamps:

00:00 - Introduction and overview with Keith Bourne

03:00 - Why reference-free evaluation matters and ragas’s approach

06:30 - Core metrics: faithfulness, answer relevancy, context precision & recall

09:00 - Code walkthrough: installation, dataset structure, evaluation calls

12:00 - Integrations with LangChain, LlamaIndex, and CI/CD workflows

14:30 - Production monitoring architecture and cost considerations

17:00 - Advanced metrics and custom domain-specific evaluations

19:00 - Common pitfalls and testing strategies

20:30 - Closing thoughts and next steps

Resources:

- "Unlocking Data with Generative AI and RAG" by Keith Bourne - Search for 'Keith Bourne' on Amazon and grab the 2nd edition

- Memriq AI: https://Memriq.ai

- ragas website: https://www.ragas.io/

- ragas GitHub repository: https://github.com/vibrantlabsai/ragas (for direct access to code and docs)

Tune in to build more reliable, scalable, and maintainable RAG systems with confidence using open-source evaluation best practices.

Agent engineering is rapidly emerging as a pivotal discipline in AI development, promising autonomous LLM-powered systems that can perceive, reason, and act in complex, real-world environments. But is this truly a new engineering frontier or just a rebranding of existing ideas? In this episode, we dissect the technology, tooling, real-world deployments, and the hard truths behind the hype.

In this episode:

- Explore the origins and "why now" of agent engineering, including key advances like OpenAI's function calling and expanded context windows

- Break down core architectural patterns combining retrieval, tool use, and memory for reliable agent behavior

- Compare leading frameworks and SDKs like LangChain, LangGraph, AutoGen, Anthropic Claude, and OpenAI Agents

- Dive into production case studies from Klarna, Decagon, and TELUS showing impact and ROI

- Discuss the critical challenges around reliability, security, evaluation, and cost optimization

- Debate agent engineering vs. traditional ML pipelines and best practices for building scalable, observable agents

Key tools & technologies mentioned: LangChain, LangGraph, AutoGen, Anthropic Claude SDK, OpenAI Agents SDK, Pinecone, Weaviate, Chroma, FAISS, LangSmith, Arize Phoenix, DeepEval, Giskard

Timestamps:

00:00 - Introduction & episode overview

02:20 - The hype vs. reality: failure rates and market investments

05:15 - Why agent engineering matters now: tech enablers & economics

08:30 - Architecture essentials: retrieval, tool use, memory

11:45 - Tooling head-to-head: LangChain, LangGraph, AutoGen & SDKs

15:00 - Under the hood: example agent workflow and orchestration

17:45 - Real-world impact & production case studies

20:30 - Challenges & skepticism: reliability, security, cost

23:00 - Agent engineering vs. traditional ML pipelines debate

26:00 - Toolbox recommendations & engineering best practices

28:30 - Closing thoughts & final takeaways

Resources:

- "Unlocking Data with Generative AI and RAG" second edition by Keith Bourne - Search for 'Keith Bourne' on Amazon

- Memriq AI: https://memriq.ai

Thanks for tuning into Memriq Inference Digest - Engineering Edition. Stay curious and keep building!