AI Support & Agents

Entity Extraction

Definition

Entity extraction is the process of pulling specific pieces of structured information — like names, order numbers, dates, products, or amounts — out of unstructured text so a system can act on them.

Also known as: named entity recognitionNERslot filling

How it works

Given a message like "I still haven't received order #10432 from March 3," entity extraction identifies #10432 as an order number and March 3 as a date. Classic approaches use named-entity-recognition (NER) models; LLM-based agents can extract entities directly and map them to the fields a tool expects.

The extracted values are what an agent feeds into a custom tool or API call — you can't look up an order without first isolating the order number from the sentence.

Why it matters for support

Entity extraction is the bridge between natural language and taking action. Combined with intent recognition, it lets an AI agent go from "the customer wants to track order #10432" to actually calling your order system and returning the live status — the difference between describing a process and completing it.

Frequently asked

What is the difference between entity extraction and NER?

Named entity recognition (NER) is the classic term for extracting entities like people, places, and dates. "Entity extraction" is used more broadly and, in support, often includes custom fields like order or account numbers.

Why does an AI agent need entity extraction?

To act on a request it must isolate the specifics — order number, email, date — from free-form text and pass them to a tool or API. Without it, the agent can understand the intent but not execute on it.

How custom tools act on live data

Related terms

Intent Recognition

Intent recognition is the process of identifying what a customer is trying to accomplish from their message — such as "track an order," "request a refund," or "cancel a subscription" — so the system can route or resolve it correctly..

Natural Language Processing (NLP)

Natural language processing (NLP) is the field of AI focused on enabling computers to understand, interpret, and generate human language — the foundation for tasks like intent recognition, sentiment analysis, and text classification..

Text Classification

Text classification is the task of automatically assigning a category or label to a piece of text — such as tagging a support ticket by topic, language, or priority..

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..

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..

Put these ideas to work

Macha is an AI agent layer that sits on top of the help desk you already run — Zendesk, Freshdesk, Front, Intercom, or Gorgias.

Start Trial