Tool Chaining: Multiple Tools in Sequence, Passing Outputs Between Tools

~15 min read

Real tasks often need more than one tool call in sequence, with one tool's output feeding the next tool's input — a natural extension of the book's single-tool CurrencyConverterTool example to multi-step, multi-tool workflows.

Tool Chaining: Multiple Tools in Sequence, Passing Outputs Between Tools is a Pro topic

Sign in, then upgrade to Pro or Power to unlock this topic and the full AI Engineering curriculum.

Key points

  • Real tasks often need multiple tool calls in sequence, with one tool's output feeding the next tool's input
  • Agent-driven chaining: the LLM itself decides, turn by turn, which tool to call next — the ReAct-style loop, extended across different tools
  • Explicit orchestration: application code defines the fixed sequence and passes outputs between tools directly
  • Agent-driven chaining is more flexible and adaptive; explicit orchestration is more predictable and easier to debug
  • Production systems often use a hybrid — explicit orchestration for known workflows, agent-driven chaining for genuinely open-ended tasks