# Accuracy & Performance

## :clipboard:Overview

The platform is designed for high accuracy and to rigorously avoid misinterpreting satellite data through a sophisticated, multi-layered approach: 

* <mark style="background-color:blue;">**Orchestration and reasoning with LangChain**</mark><mark style="background-color:blue;">:</mark> Under the hood, our system uses LangChain to coordinate various AI models and tools. This allows the assistant to effectively reason, plan its approach to your query and then use a specialized suite of capabilities on your behalf.&#x20;
* <mark style="background-color:blue;">**Deterministic geospatial analysis tools:**</mark> When you ask a question that requires data (e.g., "What was the tree cover loss in this area?"), the AI uses tools that access our analysis and map rendering services to perform deterministic geospatial calculations. These are pre-built, robust tools (not generative AI outputs) that:&#x20;
  * Execute precise geospatial analysis over your regions of interest.&#x20;
  * Generate visual outputs on demand.&#x20;
  * Crucially, return deterministic, verifiable results that come directly from our peer-reviewed GFW and Land & Carbon Lab data sources, ensuring the assistant's factual outputs are always grounded in reliable, objective data.&#x20;
* <mark style="background-color:blue;">**Grounded generative insights with Retrieval Augmented Generation (RAG):**</mark> While the core geospatial analysis is deterministic, the conversational layer and "generative insights" are powered by large language models. To ensure these LLMs provide answers that reflect real expertise and are factually correct (and don't "hallucinate"), the assistant is grounded using Retrieval Augmented Generation (RAG). This process works by:&#x20;
  * **Consulting a curated knowledge base:** Instead of relying solely on its general training, the LLM first consults our specific, curated knowledge base. This includes up-to-date layer descriptions, comprehensive metadata, internal research papers and expert guidance from WRI and Land & Carbon Lab.&#x20;
  * **Providing context to the LLM:** Relevant information retrieved from this knowledge base is provided as context to the LLM alongside your query. This ensures the assistant responds like a knowledgeable research assistant, pulling directly from our validated content.&#x20;
* <mark style="background-color:blue;">**Continuous performance evaluation:**</mark> We also run performance evaluations on the assistant. This ongoing testing ensures the tool maintains a high success rate when executing user queries and consistently delivers accurate and reliable results.&#x20;

While Global Nature Watch's AI assistant is designed to generate high-quality, reliable insights by drawing on peer-reviewed geospatial data and carefully structured methodologies, it is still improving and may occasionally produce inaccurate responses, especially when interpreting quantitative results such as graphs or charts. The underlying data and map layers themselves are deterministic (not generated by AI) but LLMs are used to explain and summarize those results, which can sometimes introduce errors.&#x20;

If you notice something that seems incorrect, please click the thumbs down button to provide feedback. Your input helps us continue improving the tool's accuracy and usefulness.&#x20;

<figure><img src="/files/itAuPOAJtypovockOdNt" alt=""><figcaption></figcaption></figure>

## :chart\_with\_upwards\_trend:Performance

*Coming soon*

We're developing metrics to evaluate system stability and AI assistant performance and will share here once they're ready.&#x20;

What Global Nature Watch metrics would you like to see? Please share ideas through the [feedback form](https://surveys.hotjar.com/860def81-d4f2-4f8c-abee-339ebc3129f3) or email <landcarbonlab@wri.org>.


---

# Agent Instructions: 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:

```
GET https://help.globalnaturewatch.org/get-started/accuracy-and-performance.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.