Skip to main content

​
What are Generation Types?

Generation types define what kind of output your prompt will produce. AgentMark supports four types of generation, each optimized for different use cases:
  • Text - Natural language responses for chatbots, content generation, and analysis
  • Object - Structured JSON data with schema validation for APIs and data extraction
  • Image - Visual content generation using models like DALL-E
  • Speech - Audio output for voice applications and text-to-speech

​
Choosing the Right Type

TypeBest ForOutput FormatExample Use Cases
TextConversational AI, content writingStringChatbots, summarization, Q&A
ObjectStructured data extractionJSON with schemaForm parsing, data normalization, API responses
ImageVisual content creationImage fileMarketing assets, illustrations, prototypes
SpeechVoice applicationsAudio filePodcasts, audiobooks, voice assistants

​
Configuration

Each generation type is configured in the prompt’s frontmatter using specific config keys: 
---
name: my-prompt
text_config:        # For text generation
  model_name: gpt-4o
  temperature: 0.7
---

---
name: extract-data
object_config:      # For object generation
  model_name: gpt-4o
  schema:
    type: object
    properties:
      name:
        type: string
---

---
name: create-image
image_config:       # For image generation
  model_name: dall-e-3
  size: 1024x1024
---

---
name: text-to-speech
speech_config:      # For speech generation
  model_name: tts-1
  voice: alloy
---

​
Loading Prompts

Use the appropriate loader method based on your generation type: 
// Text generation
const textPrompt = await client.loadTextPrompt('my-prompt');

// Object generation
const objectPrompt = await client.loadObjectPrompt('extract-data');

// Image generation
const imagePrompt = await client.loadImagePrompt('create-image');

// Speech generation
const speechPrompt = await client.loadSpeechPrompt('text-to-speech');

​
Detailed Guides

Text Generation

Natural language responses with conversation history

Object Generation

Structured JSON with schema validation

Image Generation

Visual content with DALL-E and similar models

Speech Generation

Audio synthesis with voice customization