# MCP

AI keeps evolving, and AI skills are becoming mandatory for engineers. In this article, we look at how companies assess these skills today and which approach you can use in your interview process: six formats, a rubric, and a 60-minute template.

Weekend Reading #98: AI agent terminology, Uber’s MCP Gateway, Zalando’s delegated identity broker, and Meta’s petabit-class subsea cable design.

30 AI terms in two or three plain sentences each, placed on one diagram: what the model sees, what it can call, and what runs around it. MCP, skills, hooks, subagents, RAG, workflows, and the pairs people mix up.

Once an AI agent can push to Git, prompt injection becomes an authorization problem. Six things to build before agents get write access: a scoped identity, a policy outside the model, a sandbox, MCP review, advisory CI, and traces.

AI across the software development lifecycle, from requirements and architecture to coding, testing, deployment, operations, security, and compliance. Practical guidance on AI authority, deterministic controls, human ownership, and safe engineering workflows.

Weekly engineering digest: Canva session revocations, Meta BPF scheduling, stateless MCP, and Cloudflare Kitesurf for AI agents.

This week: a comprehensive 800+ question .NET interview guide covering everything from C# fundamentals to AI and distributed systems. Airbnb goes deeper into its Sitar platform with sitar-agent — the Kubernetes sidecar that reliably delivers dynamic config at the pod level. Pinterest shares the full journey of building production Ray infrastructure on Kubernetes, from KubeRay workarounds to cost governance. And Lyft explains how their metric semantic layer creates a single source of truth for key data definitions across the organization.

Prepare for your next .NET interview with 800+ interview questions and answers covering C#, ASP.NET Core, SQL, NoSQL, microservices, distributed systems, testing, AI, Agile, desktop and mobile development. For developers, senior engineers, architects and tech leads.

In this article, we review AI, LLM, prompting, .NET AI integration, Semantic Kernel, Microsoft Agent Framework, MCP, RAG, resilience, testing, observability, security, and AI coding tools for .NET engineers.

This week: a comprehensive .NET testing guide covering everything from unit test fundamentals to gRPC contract testing. Netflix introduces MediaFM, their first tri-modal foundation model for deep content understanding. LinkedIn reveals how LLM embeddings and Generative Recommender models are powering the next generation of feed ranking for 1.3 billion users. And Pinterest walks through building a full MCP ecosystem — from registry and security to 66K monthly invocations, saving thousands of engineering hours.

This week: Uber shows how AI agents can automate design system documentation via MCP and how real-time batching solves hot-key payment bottlenecks at scale. Airbnb shares a transformer-based model for recommending travel destinations to exploratory users. And Pinterest details how unified context-intent embeddings power their Analytics Agent — now the most widely adopted internal agent at the company.

This week: featuring MCP protocol deep dive, Airbnb's dynamic configuration platform Sitar, Pinterest's 96% reduction in Spark OOM errors with Auto Memory Retries, and Lyft's LLM-powered localization pipeline for faster internationalization.

MCP is the universal standard for connecting AI agents to external tools and data. Learn what it is, how it works, and why every major AI company adopted it.

This week: Cloudflare’s MCP code mode, Uber’s database federation, Wix’s shift from prompting to AI management, and LinkedIn’s LLM-based ranking at scale.

Weekend Reading: A weekly roundup of interesting Software Architecture and Programming articles from tech companies. Find fresh ideas and insights every weekend.

This week: .NET Microservices and distributed systems interview prep, Netflix’s AI graph search evolution, LinkedIn’s job ingestion system at scale, and Dropbox’s AI platform insights.