LLM Tools
Extend LLM capabilities with task-specific tools powered by vertical AI.
Overview
Graffiticode provides LLMs with powerful tools where the LLM only needs to specify what it wants, not how to build it. Each language includes a vertical AI trained specifically for that domain, which translates natural language requirements into working code.
How It Works
- LLM specifies requirements - Natural language description of the desired outcome
- Vertical AI generates code - Domain-specific AI translates requirements to Graffiticode
- Compiler produces output - Code compiles to interactive components
- User interacts - Rendered UI collects data or displays information
The LLM doesn't need to know Graffiticode syntax. It simply describes what it needs, and the vertical AI handles the translation.
Tool Definitions
create_item
Create an interactive component from a natural language description.
| Parameter | Type | Description |
|---|---|---|
language | string | The language code (e.g., "L0152", "L0166") |
description | string | Natural language description of what to create |
name | string | Optional name for the item |
update_item
Modify an existing item with natural language instructions.
| Parameter | Type | Description |
|---|---|---|
item_id | string | The ID of the item to update |
modification | string | Natural language description of the changes to make |
get_item
Retrieve an item by its ID.
| Parameter | Type | Description |
|---|---|---|
item_id | string | The ID of the item to retrieve |
list_languages
Discover available languages and their capabilities.
| Parameter | Type | Description |
|---|---|---|
category | string | Optional category filter |
search | string | Optional search term |
get_language_info
Get detailed information about a specific language.
| Parameter | Type | Description |
|---|---|---|
language | string | The language code (e.g., "L0152") |
Vertical AI Architecture
Each Graffiticode language has its own vertical AI:
| Language | Domain | Vertical AI Capability |
|---|---|---|
| L0002 | Base Language | Core functionality shared across all languages |
| L0137 | Data Transformation | GraphQL queries, flattening, reshaping data |
| L0152 | Interactive Maps | Markers, layers, geospatial data visualization |
| L0159 | Flashcards | Learning cards, spaced repetition, memorization |
| L0166 | Spreadsheets | Formulas, cell formatting, spreadsheet assessments |
Benefits
- No syntax learning - LLMs describe intent, not implementation
- Domain expertise - Vertical AIs encode best practices for each domain
- Reliable output - Consistent, working code every time
- Iterative refinement - Use
update_itemto modify existing components