AI Integration

CutReady’s AI features are powered by a pluggable LLM backend that supports streaming responses, function calling, and multiple agent configurations.

AI chat panel with function calling — The AI assistant uses function calling to read and modify sketches in real-time

Provider Architecture

The Rust backend defines an LlmProvider trait that abstracts over different LLM services:

#[async_trait]
trait LlmProvider: Send + Sync {
    async fn complete(&self, messages: &[Message]) -> Result<String>;
    async fn complete_structured<T: DeserializeOwned>(
        &self, messages: &[Message], schema: &JsonSchema
    ) -> Result<T>;
}

This trait enables swapping providers without changing the rest of the application. Currently supported:

Provider	Auth Method	Notes
Azure OpenAI	OAuth (Azure AD) or API key	Default provider, uses Azure Foundry API
OpenAI	API key	Direct OpenAI API access

Azure Foundry API

The default Azure provider connects via the Azure Foundry API with:

OAuth authentication — Azure AD token flow with Tenant ID and Client ID
Streaming — Server-sent events for real-time response streaming
Model selection — Configurable model name (e.g., gpt-4o)

API endpoint, credentials, and model are configured in Settings → AI Provider.

Function Calling (Tool Use)

The AI assistant uses function calling to interact with the user’s project. Tool definitions are sent as part of the system prompt, and the model invokes them as needed during conversation.

Available Tools

Tool	Parameters	Purpose
`read_sketch`	sketch path	Read the current sketch’s content
`set_planning_rows`	rows array	Replace all planning rows in a sketch
`update_planning_row`	index, row data	Update a single planning row
`list_project_files`	—	List all files in the project directory
`read_note`	note path	Read a markdown note’s content
`fetch_url_content`	URL	Fetch content from a web URL for reference

Tool Execution Flow

The model returns a tool_call in its response
The frontend dispatches the tool call to the Rust backend via Tauri commands
The backend executes the operation (file read, write, or HTTP fetch)
The result is returned to the model as a tool response message
The model continues generating its response with the tool result

Prompt Design

System Prompts

Each agent has a system prompt that defines its personality and behavior:

Planner — Focused on demo structure, timing, and logical flow
Writer — Focused on engaging narration and natural voiceover language
Editor — Focused on precision, making minimal targeted changes

System prompts include the tool definitions (JSON schema) so the model knows what tools are available and how to invoke them.

Silent Mode

Sparkle button actions use silent mode (silent: true flag) on sendChatPrompt(). In silent mode:

The prompt is not displayed in the chat panel
The response is not shown as a chat message
Tool calls execute normally and update the sketch
Actions are logged only in the Activity Panel

This keeps the chat history focused on intentional conversations.

Agent Configuration

Built-in Agents

The three built-in agents (Planner, Writer, Editor) ship with CutReady and have read-only system prompts that are tuned for their respective tasks.

Custom Agents

Users can define custom agents in Settings → Agents with:

Name — Display name in the agent selector
System prompt — Custom instructions that define the agent’s behavior

Custom agents use the same tool set and model as built-in agents, but with a different system prompt that shapes the AI’s approach.

Streaming Architecture

Responses are streamed from the LLM to the frontend via Tauri Channels:

The frontend sends a chat message via a Tauri command
The Rust backend opens a streaming connection to the LLM API
Response chunks are forwarded through a Tauri Channel to the frontend
The frontend renders tokens as they arrive for a responsive feel
Tool calls are detected mid-stream and executed before continuing