Are SDKs really dead?

SDKs aren't completely dead yet, but they're becoming less relevant for modern flexible applications. They still have their place for low-level system programming, game development, and enterprise software with strict compliance needs. However, for applications requiring flexibility and adaptability, Agentic AI with Agent Skills offers a superior alternative.

What are Agent Skills?

Agent Skills are capabilities that enable AI agents to perform tasks dynamically by reasoning about goals rather than following rigid code paths. Claude Code Skills, for example, allow developers to define what should happen rather than how, letting the AI determine the best approach.

How do Agent Skills differ from traditional SDKs?

SDKs require extensive coding to handle various scenarios with static, predetermined logic. Agent Skills use AI to reason and adapt dynamically, allowing applications to respond to new challenges without manual updates. This shift from deterministic code to intelligent reasoning makes systems more flexible and maintainable.

Can I replace my existing SDK-based automations with Agent Skills?

Yes, as demonstrated by Brian Casel who rebuilt his n8n workflow as a Claude Code Skill. Many SDK-based automations can be replaced with Skills, including API integrations, testing workflows, and data processing pipelines. Check platforms like skills.sh for examples of Skills replacing complex SDK implementations.

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is a standard developed by Anthropic that revolutionized how AI systems interact with APIs. MCP Servers provide AI-powered API interfaces that enable intelligent responses and actions, reducing the need for complex SDKs and manual integration work.

What are the benefits of Agentic AI over traditional development?

Agentic AI enables goal-oriented design, dynamic adaptation to new scenarios, continuous learning and improvement, easier integration with AI services, and allows developers to focus on user experience rather than complex implementation details. This results in more maintainable and adaptable applications.

How do I get started with Agent Skills?

Start by defining high-level goals for your application rather than step-by-step instructions. Explore platforms like Claude Code Skills and browse community-built Skills at agentskills.io or skills.sh. Focus on what you want to achieve and let the AI determine the implementation approach.

Will SDKs be completely replaced by AI?

Not entirely and not immediately—SDKs may remain relevant for another decade or more in specific domains like game development, embedded systems, and highly regulated enterprise software. However, for most modern web applications and automations, Agentic AI approaches are becoming the preferred choice.

MCP Conceptos, Análisis y Guías | The control plane for MCP in real environments

SDKs are Dead: Embracing Agent Skills for Automation

What's the lesson from Brian Casel's experience about the future of SDKs, no-code workflows, and automation?

In short: SDKs are dead - well, at least for many use cases in modern application development.

Unlocking Podcast Insights with MCP

Transcripts from podcasts are treasure troves of insights, ideas, and stories. However, accessing and utilizing this wealth of information can be challenging for marketers, product managers, and content creators—especially those without deep technical expertise.

Lenny Rachitsky posted on LinkedIn about sharing transcripts of his podcast episodes, I decided to format the transcripts for easy consumption by language models and AI tools.

The MCP Connect Authority: A Zero Trust Architecture for AI

In the rapidly evolving landscape of the Model Context Protocol (MCP), architects are facing a critical decision: how to secure and govern connections between AI clients and a sprawling ecosystem of tools and data servers.

The traditional answer is a Gateway—a centralized proxy that inspects every byte. The modern answer is a Connect Authority—a distributed Zero Trust model that separates permission from traffic.

MCP Registry vs Gateway: Why Connect Authority Wins

The MCP Registry is designed as a centralized catalog and metadata service for MCP (Model Context Protocol) components. It provides discovery, verification, and governance capabilities for MCP clients and servers. The HAPI MCP Registry does not proxy traffic; instead, it acts as a mcp connection authority, issuing short-lived mcp connect descriptor tokens that authorize clients to connect directly to MCP Servers.

Why a Registry + Connect Authority Beats a Gateway

In the world of MCP (Model Context Protocol), two architectural patterns often come up for discussion: using a Registry as a Connect Authority versus deploying a traditional Gateway. While both approaches aim to manage and secure connections between clients and servers, they do so in fundamentally different ways.

In this article, we will explore why the MCP Registry + Connect Authority model often outperforms the traditional Gateway approach.

When Not to Use AI: Deterministic Workflows in Production Systems

AI is everywhere. Too everywhere. From answering "hi" to deciding how your production platform runs sanity checks, we've quietly crossed a line. Not because AI can't do these things, but because it shouldn't do all of them.

Integrate the OpenAI UI SDK for ChatGPT With MCP in 60 Seconds

You want your API to be instantly usable inside AI assistants like ChatGPT, and Web UIs. The OpenAI UI SDK plus the Model Context Protocol (MCP) lets you expose your API as structured tools that large language models can call directly.

Composable Architectures and the Future of AI Integration: Why MCP Is the Missing Link

For years, OpenAPI (OAS) has been the cornerstone of how we describe, document, and integrate APIs. It standardized how systems talk to each other — and in many ways, it made the modern internet possible.

So when the Model Context Protocol (MCP) appeared, some developers were skeptical. "Another spec?" they asked. "Why do we need this when we already have OAS?"

Using OpenAI Response API for MCP Integration

This guide demonstrates how to use the OpenAI Response API to integrate with the Model Context Protocol (MCP) for seamless, AI-driven API interactions. You will learn how to generate a REST API specification with Postman's AI Agent, deploy it as an MCP server using HAPI Server, and connect it through OpenAI's Response API for testing.

OpenAI SDK Meets MCP (Model Context Protocol)

An evolution of tool calling with MCP, thanks to OpenAI's latest SDK updates.

Step-by-step, I'll guide you through setting up an MCP server, integrating it with the OpenAI SDK, and running a complete example that showcases dynamic tool calling. By the end of this post, you'll be equipped to leverage MCP in your own OpenAI-powered applications.