Patrick Chan articles - 17 total
How MCP Leverages OAuth 2.1 and RFC 9728 for Authorization
Authorization isn’t just a checkbox in agentic systems. It’s a make-or-break layer for security,...
Turn Your OpenAPI Specs Into Agentic Tools—Instantly
What if your internal APIs could talk to AI agents without manual integration, schema rewrites, or...
Navigating the Expanding Landscape of AI Applications
From LLM Apps to Agents, Tools, and Interoperability The past two years in AI have felt...
What Are Agentic AI Tools?
A new term has been gaining traction in AI discussions: agentic tools. These tools allow AI agents —...
LangChain: From Chains to Threads
LangChain is one of the most exciting frameworks to emerge in AI development. It took what was once a...
Vibe Coding: The New Way We Create and Interact with Technology
Software development has always been about one thing: enabling humans to communicate their intent to...
LLM Function-Calling Performance: API- vs User-Aligned
Performance of API-Aligned vs User-Aligned LLM Functions Large language models (LLMs) have...
Using MCP Server to Integrate LLMs into Your Systems
As the enterprise adoption of Large Language Models (LLMs) continues to accelerate, developers face...
Building Bridges: Connecting LLMs with Enterprise Systems
Enterprise users want to harness the power of large language models (LLMs) and Generative AI (GenAI)...
Rethinking LangChain in the Agentic AI World
LangChain is undeniably a powerful tool for building modern AI-powered applications, enabling...
AI and the Monkey’s Paw: Why SaaS Will Endure
In W.W. Jacobs’ The Monkey’s Paw, a family’s wishes are granted in horrifyingly unintended ways. Each...
Simplifying Data Extraction with OpenAI JSON Mode and JSON Schemas
When I first experimented with ChatGPT-3.5 after its release, I was thrilled about its potential for...
Why Function-Calling GenAI Must Be Built by AI, Not Manually Coded
Introduction The rise of large language models (LLMs) has opened the door to...
Does Model Context Protocol (MCP) Spell the Death of RAG?
Retrieval-Augmented Generation (RAG) has been a cornerstone for enabling Large Language Models (LLMs)...
Function-Calling vs. Model Context Protocol (MCP)
Integrating Large Language Models (LLMs) with enterprise systems is transforming how businesses...
User-Aligned Functions to Improve LLM-to-API Function-Calling Accuracy
What is Function-Calling? Large language models (LLMs) excel at generating text-based...
Function-based RAG: Extending LLMs Beyond Static Knowledge Bases
RAG Defined Retrieval-Augmented Generation (RAG) effectively overcomes a significant...