Quick Start Guide
Deploy Your First Agent
Learn how to deploy your first AI agent using Hikigai's config-based deployment. No coding required.
New to Hikigai?
This guide will walk you through deploying a production-ready AI agent in under 5 minutes using our config-based approach.
Create Your Account
First, you'll need a Hikigai account to start deploying agents.
Visit login and sign in securely with your Google account.
Access the developer console immediately.
Free Tier
All new accounts include free credits to deploy and test your agents.
Create a Project
Projects help you organize related agents. Think of them as containers for your AI applications.
Navigate to the Projects page in your console
Click "Create New Project"
Enter a project name and description
Click "Create Project"
Example:
Name: Healthcare Assistant
Description: AI agents for clinical documentation and patient care
Configure Your Agent
Now you'll configure your agent using our simple form-based interface.
Open your project and click "Deploy Agent"
Select "Config-Based" deployment mode
Fill out the configuration form with your agent details
Required Fields:
Agent Name
A unique identifier for your agent (e.g., "clinical-note-summarizer")
Instruction
Tell the agent what it should do. Be specific and clear.
You are a clinical documentation assistant. Convert patient encounter transcripts into structured SOAP notes. Extract key medical information including symptoms, vital signs, diagnoses, and treatment plans.Model
Choose the AI model (gemini-2.0-flash, gpt-4, etc.)
Input Schema
Define what data your agent accepts (JSON Schema format)
{
"type": "object",
"properties": {
"transcription": {
"type": "string",
"description": "Raw patient visit transcript"
},
"patient_id": {
"type": "string",
"description": "Patient identifier"
}
},
"required": ["transcription"]
}Output Schema
Define what data your agent returns (JSON Schema format)
{
"type": "object",
"properties": {
"subjective": {
"type": "string",
"description": "Patient-reported symptoms"
},
"objective": {
"type": "string",
"description": "Clinical observations"
},
"assessment": {
"type": "string",
"description": "Diagnosis and analysis"
},
"plan": {
"type": "string",
"description": "Treatment plan"
}
}
}Pro Tip
Start with a simple instruction and schema. You can always refine them after testing your agent.
Deploy Your Agent
Review your configuration and deploy to Google Cloud Run.
Click "Preview Code" to review the generated code
Verify your agent's instruction, schemas, and settings
Click "Deploy"
Wait 2-3 minutes while your agent is deployed (you'll see real-time progress)
What happens during deployment:
- Agent code is generated from your configuration
- Docker container is built with your agent
- Container is deployed to Google Cloud Run
- Secure endpoint URL is created
- Agent is registered in your project
Deployment Time
First deployment typically takes 2-3 minutes. Subsequent deployments are faster due to caching.
Test & Invoke Your Agent
Once deployed, you can immediately test and invoke your agent.
Using the Console:
Navigate to your agent's detail page
Click "Test Agent" to open the testing interface
Enter sample input data matching your input schema
View the agent's response and verify it matches your expectations
Using the Python SDK:
from hikigai import Hikigai
# Initialize the client
client = Hikigai(api_key="your-api-key")
# Invoke your agent
response = client.invoke_agent(
agent_id="clinical-note-summarizer",
input_data={
"transcription": "Patient presents with...",
"patient_id": "12345"
}
)
# Access the result
print(response.output)Using Platform API:
curl -X POST https://api.hikigai.com/v1/agents/clinical-note-summarizer/invoke \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"transcription": "Patient presents with...",
"patient_id": "12345"
}'API Keys
Generate API keys from the API Keys page in your console.