> For the complete documentation index, see [llms.txt](https://docs.snyk.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.snyk.io/agent-security/readme.md). # Overview Secure AI-assisted development and the AI systems your Organization runs, across coding assistants, cloud AI platforms, and organization-wide AI risk Snyk secures AI-assisted development and the AI systems your Organization runs, across three areas. ## Secure coding assistants with Snyk Studio Agentic workflows speed up development, but AI-generated code can introduce vulnerabilities or insecure practices. [Snyk Studio](/agent-security/agentic-security-with-snyk-studio/agentic-security-with-snyk-studio.md) embeds security directives directly into your AI-assisted workflows, connecting the Snyk platform, your development environment, and your AI tools. Use Snyk Studio when you want to: * Guide coding assistants such as Claude Code, Codex CLI, Cursor, and Gemini CLI toward secure output as they generate code. * Run Snyk scans (Snyk Code, Snyk Open Source, Snyk IaC) directly from an agent through the local Snyk MCP Server. * Roll out consistent security directives across AI tooling in your Organization. To get started, visit [Getting started with Snyk Studio](/agent-security/agentic-security-with-snyk-studio/getting-started-with-snyk-studio.md) or jump to a [quickstart guide](/agent-security/agentic-security-with-snyk-studio/quickstart-guides.md) for your specific tool. ## Govern cloud AI platforms Beyond what an individual developer generates with a coding assistant, Snyk extends visibility to the [cloud AI platforms](/agent-security/cloud-ai-platforms/overview.md) your Organization runs, such as Anthropic's Claude Enterprise. These integrations surface AI models, approved MCP servers, and tool-level permissions as assets in your Evo inventory. ## Manage AI risk and posture with Evo by Snyk [Evo by Snyk](/agent-security/evo-by-snyk/overview.md) is the platform layer that ties the above together: it surfaces risk context for AI assets discovered by AI-SPM and Agent Supply Chain Security, lets you apply that context in policies, and raises issues when an asset violates one. Use Evo when your focus is organization-wide AI risk visibility and policy enforcement rather than a single tool or platform. ## Choosing where to start * Securing what an individual developer generates with an AI coding assistant → start with Snyk Studio. * Governing a cloud AI platform your Organization has adopted → start with Cloud AI platforms. * Getting a unified view of AI risk and enforcing policy across both → start with Evo by Snyk. --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.snyk.io/agent-security/readme.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.