> For the complete documentation index, see [llms.txt](https://docs.waveline.ai/extract/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.waveline.ai/extract/additional-material/limitations.md). # Limitations ## Highly Nested Shapes Even though our definition of [Shape](/extract/types/shape.md) does not limit nesting (placing an object inside of an object), we currently place an artificial limit of only one nesting level on requests we process. This means you can create an object that holds other fields but not other objects. Limiting nesting helps our models better process your data and return more accurate results. We haven't found a use case where deep nesting is necessary, but please [get in touch](mailto:team@waveline.ai) with us if you require it! ## Perfect Correctness Waveline Extract uses Large Language Models to produce accurate and dependable results. While we work hard to ensure excellence, it's worth mentioning that, like any AI, it isn't always perfect. We encourage you to try out our service with a range of examples and feel the excellent consistency of our output. On the off chance you spot any inconsistencies or incorrect results, don't hesitate to [reach out](mailto:team@waveline.ai). We appreciate your feedback immensely, as it helps us continually improve and fine-tune our service. --- # 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.waveline.ai/extract/additional-material/limitations.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.