Add Local OCR to a .NET AI Agent (Upload → Parse → Chat) with LiteParse
Build a .NET agent that can read receipts, PDFs, spreadsheets, and images locally by routing document parsing through a dedicated tool that looks up uploaded files, runs LiteParse, and returns clean text to the chat flow.
I Built the Same AI Agent in 5 Frameworks: What Actually Changes (and What Doesn’t)
A hands-on comparison of CrewAI, LangGraph, LlamaIndex, PydanticAI, and Microsoft Agent Framework using the same flight-assistant agent: setup, tool calling, RAG, MCP, execution flow, and what to watch for in runtime and token usage.
Hello Microsoft Agent Framework (Bye Bye AutoGen!)
Microsoft just launched Agent Framework, combining AutoGen and Semantic Kernel into one unified platform. While AutoGen will only get bug fixes (no new features) so if you're using AutoGen, it's time to plan your migration.
Connecting AutoGen Agents to Any MCP Server
Your AutoGen agents are already smart, but what if they could be 10x more powerful? In this tutorial, I show you how to connect your agents to an MCP Server, giving them access to a whole new world of tools and capabilities.
Self-Hosted Private LLM using Ollama and Open WebUI
If you're worried about sending private information across the web to your favourite chatbot, you're not alone. In this guide, I will show you how you can securely run a ChatGPT-style interface using your preferred model for complete privacy.
What the Heck is MCP? (& what it isn't)
MCP is a new protocol that lets AI models call tools, access APIs, and fetch real-time data while responding to users. Here’s how it works and how it compares to RAG.
AutoGen Team Workflows: RoundRobinGroupChat, SelectorGroupChat, and Swarm
In this post, I'm going to break down how each of the AutoGen team workflows works and how each one of them helps your team achieve its goal as efficiently as possible.
AI Is Changing Your Brain (Whether You Like It Or Not)
Ever caught yourself reaching for ChatGPT before even attempting to solve a simple problem? You're not alone. That subtle shift in how we think is happening to millions of people—and faster than most realize.
AutoGen 0.4.8 Introduces Native Ollama Support: Run AI Agents Locally
AutoGen 0.4.8 just dropped with native Ollama integration using the new OllamaChatCompletionClient. No more workarounds and API costs.
AutoGen 0.4 Tutorial - Create a Team of AI Agents (+ Local LLM w/ Ollama)
In this tutorial, we'll learn how to create AI agent teams that can take a prompt and output a YouTube shorts video automatically using AutoGen 0.4, integrate APIs like ElevenLabs & Stability AI, and run local LLMs with Ollama!
OpenAI Just Released GPT-4.5: Here's What You Need to Know
GPT-4.5 brings enhanced emotional intelligence and deeper knowledge. OpenAI says that this is their "largest model yet" but is it worth the cost? Let's find out!