# BRD Extraction Prompts - json file

> Generate FlexBase JSON import files from a BRD (or from previously extracted Markdown).

## How to Use

Tell your AI agent what you need. It will load JSON structure rules and conventions automatically.

**Example prompts you can give your AI agent:**

```
Generate a FlexBase JSON import file from this BRD
```

```
Create the JSON for just the Orders module
```

```
Extract domain services to JSON with all properties
```

```
Convert this BRD extraction markdown to FlexBase JSON
```

***

## Task Catalog

### Task 1: Quick JSON Generation

**Goal:** Generate a complete FlexBase JSON import file with all defaults applied\
**User provides:** BRD file or existing extraction markdown\
**Output:** `[ProjectName]_Flexbase_Import.json`

### Task 2: Complete JSON with Verification

**Goal:** Generate JSON with explicit verification of all rules and structure\
**User provides:** BRD file or existing extraction markdown\
**Output:** `[ProjectName]_Flexbase_Import.json` + verification checklist

### Task 3: Modules JSON Only

**Goal:** Generate only the modules array\
**User provides:** BRD file or existing extraction markdown\
**Output:** `[ProjectName]_Modules.json`

### Task 4: Domain Services JSON Only

**Goal:** Generate only the consolidated domain services array\
**User provides:** BRD file or existing extraction markdown\
**Output:** `[ProjectName]_DomainServices.json`

### Task 5: Domain Services with Properties

**Goal:** Generate domain services JSON with full attribute, relationship, and index definitions\
**User provides:** BRD file or existing extraction markdown\
**Output:** `[ProjectName]_DomainServices.json` — includes attributes, relationships, and indexes per entity

### Task 6: UI-Enriched JSON Generation

**Goal:** Generate FlexBase JSON with screen/UI metadata on each feature, capturing UI structure from BRD wireframes or derived from feature patterns\
**User provides:** BRD (with or without UI descriptions) or previously extracted Markdown\
**Output:** `[ProjectName]_Flexbase_Import.json` with `metadata.screenFlow` on every UI-facing feature

### Task 7: Screen Definition JSON Generation

**Goal:** Generate screen definitions with controls referencing features\
**User provides:** BRD (with UI descriptions or wireframes) or existing extraction markdown with screen flow data\
**Output:** `[ProjectName]_[ModuleName]_Screens.json` — one per module

***

## Key Rules (Applied Automatically)

* **3-section JSON structure** (4 sections when UI screens are present): `modules`, `domainServices`, `modulesWithFeatures`, `modulesWithScreens`
* **Every operation = one feature** — no operations array inside features
* **Module names PLURAL** PascalCase
* **Only complex validations** in JSON — skip simple attribute validations
* **Files auto-split when large** — per-module JSON files + full combined import

***

## Related

* **Markdown extraction first:** [BRD Extraction → Markdown](/flexbase-mcp-ai-prompts/brd-extraction-prompts-md-file.md)
* **After import:** [Implementation Completion](/flexbase-mcp-ai-prompts/implementation-completion-prompts.md)


---

# 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.flexbase.in/flexbase-mcp-ai-prompts/brd-extraction-prompts-json-file.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.