> For the complete documentation index, see [llms.txt](https://docs.biobox.io/guide/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.biobox.io/guide/how-to/ask-biobox-with-claude/quickstart.md).

# Example

This walks you from zero to your first grounded answer in a few minutes. This is an example question workflow. **The types of questions you can ask depend on the data you have available in your knowledge graph and how you have configured your graph schema.** 

## 1. Connect

If you haven't already, [connect Claude to BioBox and sign in](/guide/how-to/ask-biobox-with-claude/connect-claude.md). You'll know it worked when **BioBox** shows as a connected tool in your Claude client.

## 2. Ask your first question

In a Claude conversation, ask:

> <mark style="color:$primary;">**What are the top 10 gene targets for ALS?**</mark>

Claude will call BioBox behind the scenes — typically resolving *ALS* to a disease node, finding the relevant reasoning system, prioritization report, and reading its ranked scores — then answer with the actual top targets and their scores. You may see it mention the tools it used (like `search_entities`, `list_reports`, and `get_report_scores`); that's expected, and it's how you know the answer is grounded in your graph rather than the model's memory.

A good answer looks like a ranked list with scores, naming the report it came from — something you could open in the BioBox app and verify.

## 3. Follow the thread

The value of an assistant is the follow-up. Try:

> <mark style="color:$primary;">**Why was the target SOD1 deprioritized a few months ago?**</mark>

> <mark style="color:$primary;">**What other indications is SOD1 a suitable target for?**</mark>

> <mark style="color:$primary;">**What cell populations are most important for ALS?**</mark>&#x20;

> <mark style="color:$primary;">**What are the curent targets of phase 1 recuriting ALS trials and where do they rank in my target prioritization models ?**</mark>

Each of these maps to a BioBox tool ([`get_evidence`](/guide/how-to/ask-biobox-with-claude/tools/get-evidence.md), [`where_entity_ranks`](/guide/how-to/ask-biobox-with-claude/tools/where-entity-ranks.md), [`get_entity_connections`](/guide/how-to/ask-biobox-with-claude/tools/get-entity-connections.md)), and Claude chains them for you.

## Tips for grounded answers

* **Name the disease, gene, drug, or model** you care about — Claude resolves names to graph nodes, so specifics help it pick the right one.
* **Ask for the source.** "Which report?" / "Show the evidence." keeps answers traceable back into BioBox.
* **If a name is ambiguous** (a symbol that matches several nodes), Claude may ask you to pick the right one — that's the disambiguation step, not an error.
* **It won't change anything.** The MCP is [read-only](/guide/how-to/ask-biobox-with-claude.md#what-it-can-and-cant-do), so explore freely.

## Where to next

* [**Tool Reference**](/guide/how-to/ask-biobox-with-claude/tools.md) — everything Claude can call, with parameters and example responses, if you want to understand exactly what's happening under the hood.