> For the complete documentation index, see [llms.txt](https://docs.zerve.ai/zerve-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zerve.ai/zerve-docs/readme.md).

# Welcome to Zerve

Zerve is an AI platform for data and research work, where agents plan, build, run and check the work for you.

Zerve is an AI platform for data and research work, built for the quant, investment and data teams at hedge funds, banks and asset managers. You describe what you want to achieve, and Zerve's agents plan the work, fetch the data, write and run the code, check the results and keep improving, all in an environment where every step can be inspected.

## Two ways to work

Zerve has two products that share one organization. You move between them with the product switcher.

|                  | Superagents                                                                                                                     | Workspace                                                                           |
| ---------------- | ------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- |
| **In the app**   | "Missions that run themselves"                                                                                                  | "Notebooks, threads and projects"                                                   |
| **Best for**     | Long-running goals you want owned for you, such as an alpha research program, daily risk monitoring or a weekly market briefing | Hands-on work with an agent alongside you, from a quick question to a full analysis |
| **How it works** | A superagent manages a team of agents that works toward your objectives continuously, in the background                         | You work in threads and notebooks, and choose how much the agent does on its own    |

Both products use the same agents, data connections, assets and settings.

## What makes Zerve different

**Agents built for exploratory work.** Data and research work rarely follows a fixed plan. Zerve's agents are designed to form hypotheses, test them on real data, learn from what fails and try again, rather than execute a script once.

**Everything is inspectable.** Agents work in notebooks, so every result comes with the code, variables and outputs that produced it. You can open any step, check it and change it.

**Agents that check their own work.** Zerve's agents verify results before presenting them, using independent reviewers and blind re-derivation for results that matter.

**Knowledge that compounds.** Agents keep persistent learnings and memory, so each run builds on what was discovered before instead of starting from scratch.

**Runs where your data lives.** Zerve can run entirely inside your own cloud account or on your own infrastructure, including air-gapped environments.

## Where to start

| If you want to…                                 | Start here                                                                                |
| ----------------------------------------------- | ----------------------------------------------------------------------------------------- |
| Hand off a goal and let a team of agents own it | [Quickstart: your first superagent](/zerve-docs/getting-started/quickstart-superagent.md) |
| Work alongside an agent in a notebook           | [Quickstart: Evolve Mode in a notebook](/zerve-docs/getting-started/quickstart-evolve.md) |
| Understand how the pieces fit together          | [How Zerve works](/zerve-docs/getting-started/how-zerve-works.md)                         |
| Learn the vocabulary                            | [Key concepts](/zerve-docs/getting-started/key-concepts.md)                               |
| Run Zerve in your own cloud                     | [Deployment options](/zerve-docs/self-hosting/self-hosting.md)                            |


---

# 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.zerve.ai/zerve-docs/readme.md?ask=<question>&goal=<user_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.