> For the complete documentation index, see [llms.txt](https://docs.ai.neevcloud.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ai.neevcloud.com/agentic-studio/overview-1.md). # Agents Agents provide ready-to-use, AI-powered environments that allow you to build, run, and interact with intelligent workflows instantly. Built on top of secure sandbox infrastructure, agents eliminate manual setup and let you focus directly on execution. With pre-configured templates, built-in tools, and flexible interfaces, Agents enable developers and teams to move from idea to execution in seconds. ## Why Use NeevCloud Agents? When working with AI tools, coding environments, or automation workflows, setting up the right environment can slow you down. NeevCloud Agents simplify this by providing: * **Instant Environments** - Launch fully configured environments without installing dependencies or managing infrastructure * **Flexible Interaction** - Work via terminal for CLI workflows or use a browser-based UI for visual interaction * **Secure Execution** - Run everything inside isolated sandboxes with controlled network access and secure secret management * **Seamless Integrations** - Easily connect to external AI providers using API keys configured as secrets ## Key Features * **Pre-configured Agent Templates** - Choose from ready-to-use templates designed for specific workflows such as coding agents, CLI tools, or web-based environments * **Terminal and Web UI Access** - Interact with agents using: * Terminal (CLI-based interaction) * Web UI (browser-based interface) * **Secure Sandbox Execution** - Every agent runs inside an isolated sandbox with dedicated compute, filesystem access, and a ready execution environment * **Secrets Management** - Securely provide API keys and tokens required for integrations without exposing sensitive data * **Controlled Network Access** - Agents operate within defined network policies, allowing only approved outbound connections ## Who Should Use Agents * Developers building AI-powered applications * Teams running coding or automation workflows * Engineers experimenting with tools and environments * Organizations needing secure, isolated execution environments ## How Agents Work Agents are built on top of NeevCloud Sandboxes: * When you create an agent, a sandbox is automatically provisioned * The selected template is deployed inside the sandbox * The agent becomes accessible via Terminal or Web UI * The sandbox handles compute and isolation, while the agent provides the ready-to-use environment ## Important Note Agents do not run independently. Each agent is backed by a sandbox that provides the underlying compute, storage, and execution environment required for it to function. --- # 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.ai.neevcloud.com/agentic-studio/overview-1.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.