[music] Thanks everybody for uh for joining. I'm here to talk to you today about DSPI. Um, and feel free to jump in with questions or anything throughout the talk.It's, you know, I don't sp I don't plan on spending the full hour and a half or so. I know it's the last session of the day. So, um, keep it casual.Feel free to jump in. I'll start with a little bit of background. Don't want to go through too many slides.I'm technically a consultant, so I have to do some slides, but we will dive into the code for ...

AI Model Performance - Grok 4.1 Fast ranks 1 in ²-Bench for Telecom Agentic Tool Use with 93% accuracy, outperforming Claude Opus 4.5 & Gemini 3 Pro [1] - Grok 4.1 Fast costs up to 50x less than Claude Opus 4.5 [1] AI Agent Tooling - Tool calling is where the whole game is for AI agents, and Grok 4.1 Fast excels in this area [1]

Model Performance - Grok-4 is considered the top model due to its capabilities in tool calling, math, and instruction following [1] - Grok has a continuous pipeline of updates to improve its capabilities, including image generation (Grok Imagine) [1]

AI Agent Patterns - Basic responder agents primarily generate text responses [1] - Router pattern agents determine the appropriate path to take based on input [2] - Tool calling agents select and execute specific tools to accomplish tasks [3] - Multi-Agent pattern manages and coordinates multiple agents to achieve a common goal [4] - Autonomous pattern agents operate fully independently without direct human intervention [5]

Tool Calling Overview - LLM 可以访问一组工具来完成任务，这些工具由人工定义 [1] - LLM 决定何时使用这些工具以及执行的参数 [1]