> 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/prompt-library.md).
# Prompt library
Copy any prompt, adjust the field or crop, and ask. The assistant uses your account data: boundaries, soil tests, cleaned yield, satellite history, topography, and as-applied records.
### Start with a proven workflow
Use the Prompt library to select the most popular agronomic workflows in a few clicks. Choose a verified prompt for planning, monitoring, evaluation, reporting, or export. Then adapt it to your field, crop, and season.
GeoPard Ai Assistant - Agronomic intents and Prompt library
### Plan and prescribe
* Create fertilizer zones for this field.
* Build a P2O5 and K2O prescription for this field with a yield goal of 200 bu/ac corn.
* Create a lime prescription to correct pH on my most acidic fields.
* Create a variable rate seeding map for this field based on long-term productivity.
* Plan a soil sampling campaign for this farm with one sample per 3 ha.
* Which fields should I sample first this fall?
### Operate and monitor
* How did this field develop over the last 30 days on satellite?
* Compare NDVI between my two best and two worst fields this season.
* Which fields show stress right now and where should I scout?
* Summarize this season's operations log for this farm.
### Verify and evaluate
* Compare as-applied rates to the prescription on this field. Where did the machine deviate?
* Set up a rate trial on this field with three nitrogen levels.
* Show the results of my seeding trial: did higher population pay off?
* Which parts of this field need re-seeding?
### Post-harvest and economics
* Build a profit map for this field using my actual input costs.
* Which zones lost money last season?
* Compare yield between my irrigated and dryland fields.
* What was my nutrient use efficiency on corn this year?
* How much did variable rate application save compared to flat rate on this field?
### Data and export
* Import my latest harvest data from John Deere Operations Center.
* Export this prescription to John Deere as a Work Plan.
* Create a report of this field for my landlord.
* What data do you have for this field and what is missing for a fertility plan?
### Knowledge base
* According to our fertility protocol, what is the critical K level for this soil type?
* What does our product catalog recommend for this rate and crop stage?
* Summarize our trial results on row spacing for winter wheat.
{% hint style="info" %}
The assistant recommends values and shows its reasoning. You review and approve every plan.
{% endhint %}
### Related
* [GeoPard AI Assistant overview](/geopard-tutorials/product-tour-web-app/geopard-ai-assistant.md)
* [Agronomy knowledge base](/geopard-tutorials/product-tour-web-app/geopard-ai-assistant/agronomy-knowledge-base.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/prompt-library.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.