# Hopper

## Docs

- [Datasets and jobs](https://docs.hypercubic.ai/core-concepts/datasets-and-jobs.md): Datasets are the mainframe's files. Jobs are batch work submitted to JES. Hopper exposes both in browsable panels and through the agent.
- [How Hopper works](https://docs.hypercubic.ai/core-concepts/how-hopper-works.md): How the terminal, dataset and job browser, and chat agent share one mainframe session.
- [The AI agent](https://docs.hypercubic.ai/core-concepts/the-ai-agent.md): The first AI agent that understands mainframe. Hopper turns plain English into action across ISPF, JCL, JES, and CICS, reading source, submitting jobs, decoding VSAM records, and writing changes. All from chat.
- [The terminal](https://docs.hypercubic.ai/core-concepts/the-terminal.md): The terminal panel in Hopper is a TN3270 emulator. It renders the same green-screen interface mainframe users have worked with since the 1970s.
- [Tools](https://docs.hypercubic.ai/core-concepts/tools.md): Hopper's agent can read, write, compile, submit, install, and deploy on a real mainframe. Its approval model holds destructive actions until you confirm them.
- [Overview](https://docs.hypercubic.ai/index.md): Hopper is a desktop app for z/OS engineers. It bundles a TN3270 terminal, dataset and job browsers, and an AI agent that drives ISPF, writes JCL, and watches JES on your behalf. Runs on macOS, Windows, and Linux.
- [Quick start](https://docs.hypercubic.ai/quickstart.md): Install Hopper, connect to your mainframe, and run your first AI-driven task. About fifteen minutes end to end.
- [FAQ](https://docs.hypercubic.ai/resources/faq.md): What Hopper is, what it costs, what's stored where, and the questions we hear most often.
- [Security & privacy](https://docs.hypercubic.ai/resources/security.md): What Hopper stores, what it sends, what it redacts, and what stays on your laptop.