# What is agentic AI and what changes for an online store

> What agentic AI is, how it differs from generative AI and from an AI agent, and what it already does on its own in an online purchase.

URL: https://clione.ai/glossary/agentic-ai/
Lang: en

"Agentic AI" does not name a product or a specific model: it describes **what a system does with a model**. A chat that answers you is not agentic; a system that takes a request, decides the steps, goes into other sites or apps and hands back the finished job is. A store cares because some of the people who visit its product pages, compare prices and reach the cart are no longer people, but systems acting for them, with rules of their own. The part that does the work is the [AI agent](/glossary/ai-agent/), and its application to shopping has a name of its own, [agentic commerce](/glossary/agentic-commerce/). This entry answers the question that comes before both: what makes a system agentic.

## How it works

Google Cloud defines it as a form of AI centered on **deciding and acting with autonomy**: where traditional AI responds to commands or analyzes data, agentic AI can set goals, plan and carry out tasks with minimal human intervention.[^google-cloud-agentic] It describes how it works as a five-step loop:[^google-cloud-agentic]

1. **Perception.** It gathers information from different sources: databases, interfaces, text or images.
2. **Reasoning.** A [large language model](/glossary/llm/) ([LLM](/glossary/llm/)) analyzes that information, understands the context and proposes solutions.
3. **Planning.** It sets goals, breaks them into smaller steps and decides how to meet them.
4. **Action.** It carries out the tasks, makes decisions or interacts with other systems.
5. **Reflection.** It evaluates whether what it did worked and uses the result to adjust its plans.

### What sets it apart from generative AI

For Google Cloud, agentic AI is a subset of generative AI: the part that organizes and runs agents that use an LLM as a "brain" to act through tools. It goes beyond creating content and beyond [tool calling](/glossary/tool-calling/) (_function calling_) because it **executes actions in the underlying systems to meet higher-level goals**. Its example: generative AI writes the materials for a campaign; agentic AI publishes them, tracks their performance and adjusts the strategy based on the results.[^google-cloud-agentic]

### More or less agentic

Anthropic uses "agentic systems" for all these variants and separates two kinds. **Workflows** orchestrate the model and its tools along paths set in advance in the code. **Agents** direct their own process and decide on the fly which tool to use and when.[^anthropic-agents] That is why it helps to think in degrees: a system is more agentic the more it decides and the less is written in advance.

That autonomy has a price, and Anthropic says so plainly: agents fit open-ended problems where you cannot predict how many steps will be needed, but **they cost more and errors compound** from one step to the next. It recommends testing them thoroughly in sandboxed environments, with safeguards, stopping conditions (a maximum number of iterations, for example) and pauses to ask a person for input at checkpoints or when they get stuck.[^anthropic-agents]

## What it already does in a purchase

Commerce is one of the places where agentic AI has gone from demo to product. On November 13, 2025, Google began rolling out an [agentic checkout](/glossary/agentic-checkout/) in US Search: you say which product you want to track, with size, color and what you are willing to spend; it alerts you when the price drops within that budget and offers to have **Google buy it for you on the store's site with Google Pay**, always with your permission. It launched with Wayfair, Chewy, Quince and some Shopify stores. The same day it introduced another agentic feature that calls nearby stores to ask whether they have a product, at what price and with which promotions, in categories such as toys, health and beauty, or electronics, also in the United States.[^google-agentic-checkout]

Once the system pays, the question is who authorized it. The [AP2 (Agent Payments Protocol)](/glossary/ap2/) distinguishes two cases: the person approves the specific order, or signs a set of conditions beforehand and lets the agent buy on its own within them; if the order falls outside what was signed, the store can send it back to the person for approval.[^ap2-flows]

## In a store

A **fictional example**: a person asks an assistant with an agent mode for "waterproof trail running shoes, size 9, for under a hundred dollars, arriving before Friday." Here is what the system does in your store, step by step, and what it needs to find:

| Step in the loop | What the system does                                       | What it needs from your [product page](/glossary/product-page/)                     |
| ---------------- | ---------------------------------------------------------- | ----------------------------------------------------------------------------------- |
| Perception       | Reads product pages from several stores                    | Text that can be read without opening tabs or images                                |
| Reasoning        | Discards the ones that are not waterproof or lack the size | [Product attributes](/glossary/product-attributes/) written down, not assumed       |
| Planning         | Picks a store and decides the order: size, cart, shipping  | [Product variants](/glossary/product-variants/) that can be selected without tricks |
| Action           | Adds to the cart and reaches payment                       | Price, stock and shipping costs visible before the last step                        |
| Reflection       | Checks whether the delivery window meets the request       | The delivery date on the page itself                                                |

Each row is a point where the request can leave your store for another. Because errors compound,[^anthropic-agents] one ambiguous piece of data in the reasoning step is enough for the system to drop your product page.


That agentic AI, an AI agent and a _chatbot_ are the same thing. Google Cloud separates them: **agents are the parts and agentic AI is the system that coordinates them**; an agent focuses on one task, and agentic AI uses several for complex workflows.[^google-cloud-agentic] A _chatbot_ that only answers, without acting in any system, is neither: it is generative AI.


## How to check

1. **Make the request yourself.** Ask an assistant with an agent mode to buy a specific product from your store, with a size and a budget, and stop it before payment. Note at which step it hesitates or stalls.
2. **Read your product page without images or tabs.** Price, stock, variants, shipping and delivery time have to be in the page's text.
3. **Look in your logs for the visits a system makes on a person's behalf.** [Perplexity](/glossary/perplexity/), for example, identifies its own as Perplexity-User, distinct from its [crawler](/glossary/web-crawler/), and warns that, because a user requests them, **they generally do not follow the rules in [`robots.txt`](/glossary/robots-txt/)**.[^perplexity-bots]
4. **If you use an agent in your own store**, for customer service or returns, give it stopping conditions and checkpoints where a person decides, as Anthropic recommends.[^anthropic-agents]
5. **If you sell in the United States on Shopify**, ask your platform whether your products are included in Google's agentic checkout.[^google-agentic-checkout]

## Related concept: AI agent

An AI agent is the unit: a system that receives a task and carries it out with its tools. Agentic AI is the property and the whole system: **how much it decides on its own and how it coordinates one or several agents** for a larger goal. Google Cloud compares it to a toolbox: the agents are the tools, and agentic AI is using them in a coordinated way to build the whole house.[^google-cloud-agentic] When the goal is buying, the term that covers it is agentic commerce.

To go further, the [agentic commerce reading path](/learn/agentic-commerce/) lays out the agents, the protocols and the payments.