panda

TLDR: This post shows how PyRIT’s executor enables practical multi-agent LLM red teaming by letting one model actively attack another. Using a local Ollama setup, I focus on the Multi-Turn strategy .

TLDR: Introduces Microsoft Agent Framework (Python/.NET) and focuses on workflow orchestration. Covers agent orchestration without workflows, the motivation for explicit workflows, building blocks of workflows (executors, edges), integration with Dev UI, and how MCP tools can be part of workflows.

TLDR : Outlines using Microsoft Fabric Variable Libraries to manage environment-specific configurations in CI/CD without mutating JSON. Walks through prerequisites (Dev/Test/Prod workspaces), CI/CD flow with Azure DevOps pipelines, design of variable libraries and automated variable resolution, limitations, and an alternative approach via ADO + fabric-cicd

Focuses on security in MCP. Observes MCP’s expanded attack surface and need for robust auth. Describes updated MCP spec with OAuth 2.1 flows, OAuth resource server classification for MCP, dynamic client registration, PKCE enforcement, resource indicators, and JSON-RPC batching.

TLDR: Explains the Model Context Protocol (MCP): its architecture, core components (Host App, MCP Client/Server, tools/resources), and JSON-RPC flow. Provides a proof of concept building an MCP server (Python + FastMCP) to fetch Azure inventory/recommendations, including example code and VS Code integration.