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 . where attacker, target, and scorer models are orchestrated in a loop, with scoring and stopping logic handled entirely by the executor. The result is a reproducible, extensible way to automate jailbreak discovery. ...
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. Demonstrates workflow design (conditional routing, state handling) and contrasts with manual orchestration ...
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. Concludes MCP standardizes tool invocation but isn’t transformative yet and outlines next topics in series ...