> 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/superagents/batches/survey.md).

# Survey

Run the same deep analysis across many entities, each with its own team.

A **Survey** batch runs the same deep analysis across many entities, such as companies, regions or funds, where each one needs a whole team rather than a single worker.

## When it's used

Use a Survey when each item in the list is a substantial piece of work. For example:

* Reviewing each of 30 portfolio companies against the same due diligence checklist
* Analysing credit conditions in each of a dozen regions
* Assessing each fund in a manager shortlist on the same criteria

## How it works

1. The superagent defines the analysis and the list of entities, called **slices**.
2. Each slice gets its own coordinator, who builds and runs a team for that entity.
3. The slices run in parallel, and the results are combined when they're done.

A survey can be **open-ended**, which means it stays open after the first pass, so slices can be added, removed or rerun later. That suits work where the list changes over time, such as a watch list of companies.

## How it's different from Map

|                    | [Map](/zerve-docs/superagents/batches/map.md) | Survey                       |
| ------------------ | --------------------------------------------- | ---------------------------- |
| **Each item gets** | One run by a worker                           | Its own coordinator and team |
| **Best for**       | Many small, identical tasks                   | Fewer, larger analyses       |
| **Example**        | Score 500 stocks on one metric                | Review 30 companies in depth |

## Example request

> For each company in our private credit portfolio, review the latest quarterly financials against our covenant checklist and flag any that are close to a breach. Keep the survey open so we can add new companies as we lend to them.


---

# 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/superagents/batches/survey.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.