Apr 25
Loading video player...
One tool per agent? Time for real toolkits. In this hands-on tutorial, you'll give each agent its own set of tools — the research agent gets a gold price fetcher AND a currency converter, while the analysis agent gets a portfolio calculator. For the first time, your tools take typed parameters — Claude reads the function signatures and docstrings to decide what values to pass. What we cover: - Tools with parameters — Claude reads type hints and Args docstrings to pass the right values - Agent-specific toolkits — different agents bound to different tools via bind_tools - Separate ToolNodes — each agent's tools execute independently - Multi-tool chaining — Claude calls two tools in sequence to answer one question - The Frankfurter currency API — free, no API key required New concepts: Tools with parameters, multiple tools per agent, agent-specific toolkits, multi-tool chaining This is Tutorial 6 in the AI Orchestration from Zero series. ← Tutorial 7 (Security Fundamentals): https://youtu.be/YMQsCpsiP7I ← Tutorial 5 (Multi-Agent Basics): https://youtu.be/nx6HaySGOlc ← Tutorial 4 (State and Memory): https://youtu.be/5UQcHi538-c ← Tutorial 3 (Tool-Using Agent): https://youtu.be/4eUdFquzulU ← Tutorial 2 (Setup + Hello World): https://youtu.be/uGmhG_zSWOs ← Tutorial 1 (Concepts): https://youtu.be/EgIULrnjsL8 📂 Code on GitHub: https://github.com/lngo/ai-orchestration-from-zero/tree/main/tutorial-06 ⏱️ Timestamps: This series covers all three approaches to AI orchestration: → Phase 1 (Tutorials 2–7): Developer-controlled orchestration with LangGraph → Phase 2 (Tutorials 8–9): Autonomous agents with Claude Code → Phase 3 (Tutorials 10–11): LLM-as-orchestrator — agent teams and hybrid architectures 🔔 Subscribe for the full series: @AIForYourWork #LangGraph #CustomTools #AIOrchestration #CurrencyAPI #ClaudeAPI #PythonTutorial #AIForYourWork #BuildMoreHireLess #ToolParameters #AgentToolkits