<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tool Use &amp; Function Calling on DATATWEETS</title><link>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/</link><description>Recent content in Tool Use &amp; Function Calling on DATATWEETS</description><generator>Hugo</generator><language>en</language><copyright>Copyright (c) 2025 Datatweets</copyright><lastBuildDate>Sat, 27 Jun 2026 09:00:00 +0200</lastBuildDate><atom:link href="https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/index.xml" rel="self" type="application/rss+xml"/><item><title>Lesson 1 - Why LLMs Need Tools</title><link>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-1-why-llms-need-tools/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-1-why-llms-need-tools/</guid><description>Tool use turns a chatbot into something that can act. Understand the three limits of a text-only model and walk through your first complete tool-use round-trip.</description></item><item><title>Lesson 2 - Defining Tools and Schemas</title><link>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-2-defining-tools-and-schemas/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-2-defining-tools-and-schemas/</guid><description>A tool is only as good as its definition. Learn the three parts of a tool, see how the description decides when the model calls it, and control selection with tool_choice.</description></item><item><title>Lesson 3 - The Tool-Use Loop</title><link>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-3-the-tool-use-loop/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-3-the-tool-use-loop/</guid><description>A single tool call is rarely enough. Build a proper loop that dispatches tools by name, handles several rounds of calls, and runs until the model is done — then meet the SDK tool runner.</description></item><item><title>Lesson 4 - Parallel Tools, Errors, and Strict Schemas</title><link>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-4-parallel-tools-errors-strict/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-4-parallel-tools-errors-strict/</guid><description>Real agents must do more than one tidy round-trip. Learn to execute several tool calls from a single turn, report failures the model adapts to, and lock down arguments with strict schemas.</description></item><item><title>Lesson 5 - Guided Project: A Multi-Tool Workflow Agent</title><link>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-5-guided-project-multi-tool-agent/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/tool-use-and-function-calling/lesson-5-guided-project-multi-tool-agent/</guid><description>The module capstone: build a working multi-tool agent step by step — a toolbox of real functions, a name-to-function dispatcher, a loop that handles many tool calls and errors per round, a tool-aware system prompt, and a REPL — then watch one question drive more than one tool.</description></item></channel></rss>