> For the complete documentation index, see [llms.txt](https://docs.verygoodsecurity.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.verygoodsecurity.com/agentic-commerce/agentic-commerce-overview.md). # Agentic Commerce Overview Learn how VGS enables Agentic Providers to securely collect, tokenize, and share payment credentials without ever exposing raw information. Agentic Commerce is a new model for enabling AI systems, like autonomous agents or LLMs, to securely make decisions and take actions in commerce flows. Instead of people shopping online using a typical browser or app-based e-commerce experience, software agents can now collect data, tokenize it, trigger payments, and interface with third-party APIs on behalf of users. VGS provides AI and Agentic providers the secure infrastructure they need to collect, tokenize, store, and share payment credentials **without ever handling raw sensitive data**. ### Watch: What Is Agentic Commerce? {% embed url="" %} *** ### Key Capabilities * **Collect payment credentials securely** using VGS Collect's PCI-compliant hosted fields * **Tokenize and store cards** via the VGS Card Management Platform (CMP) * **Share payment credentials** to any PSP or payment system for card-on-file and subscription payments * **Use network tokens + cryptograms** to process payments agentically * **Autofill checkout forms** securely via headless or operator browser flows ## Useful Resources [Agentic Developer Toolkit](https://github.com/vgs-samples/vgs-agent-toolkit/tree/main)
[Blog: Why Agentic Commerce? Why now? And what is it?](https://www.verygoodsecurity.com/blog/posts/why-agentic-commerce-why-now-and-what-is-it) *** --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.verygoodsecurity.com/agentic-commerce/agentic-commerce-overview.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.