> For the complete documentation index, see [llms.txt](https://docs.neurolabai.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.neurolabai.io/start-using-neurolab/first-query.md).

# Run Your First Query

In the first walkthrough, we'll be using **Donepezil** to showcase several of the available Neurolab modules. Donepezil (a cholinesterase inhibitor with FDA approval for treatment of dementia) presents an example of a known compound chosen to demonstrate the most mature application path. The purpose of this walkthrough is to become familiar with Neurolab's default workflow, not to prescribe a given conclusion about this (or any other specific) compound.

## Compound Input: Submitting the Query

1. Keep the input in **Basic** mode.
2. Locate the `// Enter_Compound_`  box. and enter `Donepezil` 
3. Submit the query.

Basic mode sends the name through the known-compound workflow. The application requests the default top-five output and asks for knowledge-graph support where available.

![Donepezil entered in the Basic compound input before submission](https://3908477117-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fgze1K0yofnhFNmM9nEyt%2Fuploads%2Fgit-blob-307f01d39a08da765cc806beed284520eb7c3b5d%2F01-query.jpg?alt=media)

## 2. Watch the InferenceStream complete

The **InferenceStream** module displays a real-time stream of the inference in progress, and this stage also rapidly streams the application's transition to a finalized report. A progress event describes processing state; it is not itself a scientific result.

If the name resolves to the release knowledge graph, the final report opens the other workspaces. If the application cannot resolve a name, you will be asked to provide a SMILES string instead. That response means “the known route needs a structure,” not that the compound is invalid.

## 3. Read scope before content

Before focusing on the first-ranked item, find the report’s route, release identity, reliability information, warnings, and any abstention or unavailable fields.

For this walkthrough, confirm that the result followed the **known-compound** route. The exact returned rankings can change with the model, KG, and application release; use the values in the current report rather than a screenshot or copied example from another version.

## 4. Move through the workspaces

Use the available workspaces in this order:

1. **Inference** — confirm the request reached a finalized report.
2. **Section Inspector** — choose MoA, Cognition, or Side Effects and read rank, raw score, reliability, report evidence, and separately grouped literature.
3. **Data Explorer** — try a bounded request such as “compare the top two mechanisms.” Confirm that the report ranking remains unchanged.
4. **Raw Payload** — compare the formatted sections with the exact response fields.
5. **Chat Report** — attach one report section and ask a narrow question about what it says and what it does not establish.
6. **Knowledge Graph** — open the same section’s report-local support/context view and inspect source, scope, coverage, and truncation metadata.
7. **Brain Explorer** — inspect available brain channels and read the channel’s method label before interpreting its colors or ranks.

## 5. Export or organize the research artifact

From Raw Payload, export the full report JSON or a selected section. From the Knowledge Graph Explorer, export the available graph artifact as Graph JSON and, depending on renderer, SVG or PNG.

If account-based organization features are enabled for you, you may also be able to associate the result with a developing [Research Workbench](/organize-and-compare-research/research-workbenches.md) or [Molecular Portfolio](/organize-and-compare-research/molecular-portfolios.md). Preserve the original release identity in either case.

Keep these identifiers with any saved artifact when present:

* compound identity or submitted structure;
* route;
* model version;
* knowledge-graph release;
* schema or report version;
* generation time; and
* warnings, applicability, and abstention state.

## A good first follow-up question

Attach a single report section and ask:

> What kind of claim is this section making? What evidence is attached to this exact field, and what would I need to verify independently?

That question makes the assistant explain scope instead of merely paraphrasing the top-ranked label.

## If something goes wrong

* **Name not found / SMILES required:** switch to Advanced input and supply a reviewed structure.
* **Request error:** retry once after checking the name. Do not repeatedly submit sensitive data.
* **Empty or withheld field:** treat the absence as information; do not ask the assistant to invent a replacement.
* **Unexpected route:** stop and inspect the submitted name/SMILES before interpreting the result.

***

Next: [Choosing an Input Route](/start-using-neurolab/input-routes.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.neurolabai.io/start-using-neurolab/first-query.md?ask=<question>&goal=<endgoal>
```

`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.