Shopify
Stripe
Slack
Notion
Google Workspace
Confluence
Tool Use
定義
Tool use is the ability of an AI model to invoke external functions, APIs, or systems — like looking up an order or issuing a refund — instead of only generating text, so it can act on real data rather than just describe it.
How it works
The model is given a set of tools, each described with a name, purpose, and expected inputs. When a request requires live data or an action, the model outputs a structured call — the tool name plus arguments — which the surrounding system executes. The result is fed back to the model, which uses it to continue reasoning or write its final answer.
In customer support this is what lets an AI agent read a customer's account from a backend, apply a policy, and take an action such as updating a record — all inside a single conversation.
Why it matters for support
Tool use is the mechanism that turns a text-only assistant into something that can resolve tickets. Without it, an AI can only explain how to do something; with it, the AI can actually do the thing on the customer's behalf.
- Grounds answers in live data instead of static text
- Enables actions like refunds, updates, and lookups
- Is the technical foundation of agentic AI
よくある質問
Is tool use the same as function calling?
Largely yes. "Function calling" is the model producing a structured request to run a named function; "tool use" is the broader term for the model invoking any external capability. The terms are often used interchangeably.
How does tool use differ from RAG?
RAG retrieves reference text to ground an answer; tool use lets the model call a function that can read live data or perform an action. Many agents combine both.
関連用語
Function Calling
Function calling is a capability that lets a language model request that a predefined function or API be run — returning the function name and structured arguments — so the model can fetch live data or take actions instead of only generating text..
Agentic AI
Agentic AI is AI that doesn't just answer questions but takes actions — it plans multi-step tasks, calls tools and APIs, and works toward a goal end to end with little or no human intervention..
Custom Tools
In Macha, a custom tool lets an AI agent call any HTTP API endpoint you configure — so an agent can read live data or take an action in a system Macha doesn't have a built-in connector for, without waiting for a marketplace app..
AI Agent
An AI agent is a software system that uses a language model to understand a request, decide what to do, and take actions — calling tools, retrieving data, and completing tasks — rather than just returning a single scripted answer..
Retrieval-Augmented Generation (RAG)
Retrieval-augmented generation (RAG) is a technique where an AI model retrieves relevant information from your own knowledge sources at query time and uses it to ground its answer, instead of relying only on what it memorized during training..
アイデアを実装に
Macha は既に運用中のヘルプデスク (Zendesk、Freshdesk、Front、Intercom、Gorgias) の上に載る AI エージェント層です。
トライアルを開始