Yachtsy Docs
Get free API Key
Yachtsy Models

Yachtsy Agent

General sailing assistant with intelligent routing and conversational AI for all your sailing questions.

Overview

Yachtsy Agent is the router-based model that automatically determines the best approach for your sailing question and routes it to the appropriate specialized tool or provides direct conversational assistance.

Best For: General sailing questions, conversational assistance, mixed queries that might need different types of expertise

Key Features

  • Intelligent Routing: Automatically selects the best tool for your question
  • Conversational AI: Natural dialogue for sailing advice and guidance
  • Multi-tool Access: Can access listings, research, surveys, and general knowledge
  • Chunked Streaming: Optimized streaming for mixed content types

When to Use

Choose yachtsy-agent when you:

  • Have general sailing questions
  • Want conversational assistance
  • Aren't sure which specialized model to use
  • Need mixed responses (advice + data + recommendations)

Usage Examples

Basic Sailing Questions

from openai import OpenAI

client = OpenAI(
    base_url="https://api.yachtsy.ai/v1",
    api_key="your-api-key"
)

response = client.chat.completions.create(
    model="yachtsy-agent",
    messages=[{
        "role": "user",
        "content": "I'm planning my first offshore passage. What should I prepare?"
    }],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Equipment Recommendations

const response = await client.chat.completions.create({
    model: 'yachtsy-agent',
    messages: [{
        role: 'system',
        content: 'You are helping a sailor choose equipment for their boat.'
    }, {
        role: 'user', 
        content: 'What autopilot system would you recommend for a 35ft sloop doing coastal cruising?'
    }],
    temperature: 0.7
});

Navigation Planning

curl -X POST https://api.yachtsy.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "yachtsy-agent",
    "messages": [{
      "role": "user",
      "content": "Plan a route from San Francisco to Monterey Bay. Include timing, weather considerations, and key waypoints."
    }]
  }'

Conversation Context

Maintain context for better assistance:

messages = [
    {"role": "system", "content": "You are helping with sail trim and boat performance."}
]

# First question
messages.append({
    "role": "user", 
    "content": "My boat feels sluggish upwind. What could be the issue?"
})

response = client.chat.completions.create(
    model="yachtsy-agent",
    messages=messages
)

# Add response to conversation
messages.append({
    "role": "assistant", 
    "content": response.choices[0].message.content
})

# Follow-up with boat details
messages.append({
    "role": "user",
    "content": "It's a 1995 Catalina 34 with a 110% genoa and full-batten main. The boat has been recently antifouled."
})

response = client.chat.completions.create(
    model="yachtsy-agent",
    messages=messages
)

Router Behavior

The agent automatically routes questions to appropriate tools:

Automatic Tool Selection

  • Boat listings queries → Routes to listings database
  • Technical specifications → Routes to boat profile data
  • Market analysis → Routes to market data tools
  • General sailing → Provides conversational assistance

Example Routing

# This will automatically route to listings search
response = client.chat.completions.create(
    model="yachtsy-agent",
    messages=[{
        "role": "user",
        "content": "Show me Catalina 34 boats for sale under $50k"
    }]
)

# This will provide conversational sailing advice
response = client.chat.completions.create(
    model="yachtsy-agent", 
    messages=[{
        "role": "user",
        "content": "How do I reef a mainsail in heavy weather?"
    }]
)

Performance Characteristics

  • Response Time: 5-15 seconds (depends on routing)
  • Streaming: Chunked streaming (10-15 words per chunk)
  • Context Length: 4096 tokens
  • Temperature Range: 0.0-1.0 (default 0.7)

Best Practices

System Messages

Use system messages to set context:

{
  "role": "system",
  "content": "You are helping a beginner sailor learn basic sailing techniques. Explain concepts clearly and emphasize safety."
}

Temperature Settings

  • 0.1-0.3: Factual information and specifications
  • 0.4-0.7: Balanced advice and recommendations
  • 0.8-1.0: Creative problem-solving and trip planning

Question Formatting

Good examples:

  • "What's the best 35ft sailboat for coastal cruising with a $150k budget?"
  • "How do I troubleshoot my furling system that's jamming?"
  • "Plan a sailing route from Florida to the Bahamas in March"

Less effective:

  • "Tell me about boats" (too vague)
  • "What should I do?" (no context)
  • "Help me" (no specific question)

Error Handling

try:
    response = client.chat.completions.create(
        model="yachtsy-agent",
        messages=[{"role": "user", "content": "sailing question"}]
    )
    return response.choices[0].message.content
    
except Exception as e:
    if "401" in str(e):
        return "Authentication failed. Check your API key."
    elif "429" in str(e):
        return "Rate limit exceeded. Try again later."
    else:
        return f"Error: {str(e)}"

Integration Examples

Vercel AI SDK

import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

const { text } = await generateText({
  model: openai('yachtsy-agent', {
    baseURL: 'https://api.yachtsy.ai/v1',
    apiKey: process.env.YACHTSY_API_KEY,
  }),
  prompt: 'What are the key factors in choosing a cruising sailboat?',
});

LangChain

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="yachtsy-agent",
    openai_api_base="https://api.yachtsy.ai/v1",
    openai_api_key="your-api-key"
)

response = llm.invoke("Explain the different types of sailing rigs and their advantages")

Next Steps

Usage

Overview of Yachtsy's specialized AI models and how to choose the right one for your sailing application.

Deep Research Agent

Comprehensive research and analysis with real-time streaming for market studies and detailed investigations.