# Generate Diagrams

LLMs can be leveraged to write code for models that represent your software application. 

Since GitBook, the platform we're using to document GDF, has a native integration with MermaidJS, we we use ChatGPT to create a diagram demonstrating digramming functionality. 

## Example: Creating a systems diagram in using ChatGPT

### Prompt:  

{% code title="prompt:" overflow="wrap" %}

```
create a diagram in mermaid js showing how a web app connects to an api and the api connects to a database with details leveraging aws cloud infrastructure and a react native mobile app
```

{% endcode %}

### Response: 

{% @mermaid/diagram content="graph TD;
subgraph AWS Cloud Infrastructure
A(Web App)-->B(API Gateway);
B-->C\[Lambda Function];
C-->D\[Database];
E(Mobile App)-->B;
end

```
subgraph Details
    B-->F[Authentication];
    C-->G[Data Validation];
    C-->H[Data Processing];
    D-->I[Data Storage];
    E-->J[Authentication];
    E-->K[Data Retrieval];
end

subgraph AWS Services
    L[S3]-->M[CloudFront];
    D-->N[RDS];
end

subgraph Deployment
    O[CodePipeline]-->C;
    O-->P[CodeBuild];
    P-->Q[Elastic Beanstalk];
    Q-->A;
    Q-->B;
end
```

" %}

### Summary

Utilizing prompts in generative AI can be beneficial in software development as it accelerates code generation and provides valuable insights by taking advantage of the knowledge of bicycle-app-config technologies like JavaScript, React, Next.js, Chakra-UI, Axios, Node.js, MongoDB, GitHub, and AWS.


---

# 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://docs.gdf.ai/gdf-full-stack-engineering/subject-knowledge-areas/generation/generate-diagrams.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.