A capability of language models to request a specific function by name with structured inputs, letting frameworks such as Semantic Kernel run application code and return the result to the model.
Plugins and functions, planning and function calling, memory and RAG, connectors and prompts are the pieces inside. · Semantic Kernel - Simply Explained
Most organizations think they're building AI agents, but in reality they're still creating advanced chatbots. This episode explains why the future of Microsoft AI lies beyond conversational interfaces and focuses on Graph-powered, enterprise-grade agents that…
This episode explains why attempts to integrate AI into enterprise systems fail not because of model intelligence, but because of unbounded action and brittle integrations. The core claim is that the Model Context Protocol (MCP) is not a plugin system, API…
Learn what Microsoft's Semantic Kernel is, how plugins and function calling work, and how to connect your code to LLMs. Plain English guide. Semantic Kernel is the layer under Microsoft's AI tools that almost nobody explains. It's a free, open-source kit that…
Timeline of episodes about Function calling
Frequently asked questions
What is the Model Context Protocol?
The episode says MCP is not a plugin system, API wrapper or merely standardized function calling. Those descriptions miss the point and lead teams back to brittle glue patterns. MCP is about bounded, governable AI actions. · From the episode: Model Context Protocol vs Custom AI…
Short info above, community knowledge below: add practical tips, examples or corrections. New contributions are reviewed first; trusted members publish directly.
Experts and companies for this topic
Nobody has listed this topic yet. Add it to your profile.