> For the complete documentation index, see [llms.txt](https://docs.geopard.tech/geopard-tutorials/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.geopard.tech/geopard-tutorials/product-tour-web-app/geopard-ai-assistant/agronomy-knowledge-base.md).
# Agronomy knowledge base
The Agronomy knowledge base grounds the assistant's answers in your approved documents. Upload the material your agronomy runs on. The assistant retrieves it at query time and cites it in recommendations.
### What to upload
Product labels, crop recommendations, trial results, application rates, positioning guidance, safety notes, compatibility details, and regional rules.
### Supported files and limits
* Formats: PDF, TXT, MD, HTML, HTM, DOC, DOCX, CSV, XLS, XLSX.
* Up to 50 MB per file.
* Up to 500 MB per knowledge base.
* You can create multiple knowledge bases and build them with colleagues.
### Create a knowledge base
{% stepper %}
{% step %}
**Open knowledge base settings**
Open the [Agronomy knowledge base](https://app.geopard.tech/knowledge-base).
{% endstep %}
{% step %}
**Create and name it**
Name the knowledge base for its purpose. For example, "Corn Belt fertility 2026" or "Crop protection catalog".
{% endstep %}
{% step %}
**Upload documents**
Add files in any supported format. Processing time depends on file size. Typical processing time - 10 seconds.
{% endstep %}
{% step %}
**Verify grounding**
Ask the assistant a question that only your documents answer. The response should cite the uploaded source. If it does not, check that the document finished processing.
{% endstep %}
{% endstepper %}
### Who sees what
* Organizations share one knowledge base across the organization. Sales, advisory, and operations teams use the same guidance.
* Standalone users have a private knowledge base.
* Content is retrieved only from the current user or organization context. It stays isolated between users and organizations.
* Your documents are never used to train any AI model.
### Knowledge base vs Response Style
The knowledge base controls factual context. AI Response Style controls presentation: wording, units, structure, and citation rules. Change how answers read without touching approved source material.
Use AI Response Style to guide the assistant’s wording and response structure.
### Related
* [GeoPard AI Assistant overview](/geopard-tutorials/product-tour-web-app/geopard-ai-assistant.md)
* [Prompt library](/geopard-tutorials/product-tour-web-app/geopard-ai-assistant/prompt-library.md)
* [AI Assistant FAQ](/geopard-tutorials/product-tour-web-app/geopard-ai-assistant/precision-agriculture-ai-assistant-faq.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 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.geopard.tech/geopard-tutorials/product-tour-web-app/geopard-ai-assistant/agronomy-knowledge-base.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.