Quick Start
Get up and running with Connic in under 5 minutes. This guide walks you through creating a project, deploying an agent, and triggering your first run.
Prerequisites
• Python 3.10+ installed
• A GitHub account
• An API key for your model provider (e.g., Google AI, OpenAI)
Create a Project in Connic
Create a new project in the Connic dashboard. The wizard will guide you through connecting your repository.
Go to Projects and click Create Project
Click Connect and authorize Connic to access your repositories
Select the repository you want to connect
Enter a project name and select your deployment region
Create an environment (e.g., Production) and select the branch to deploy from
Add your API key for your model provider (e.g., OpenAI, Anthropic, Gemini)
Set Up Your Local Repository
Install the Connic SDK and initialize your project.
pip install connic-composer-sdkconnic init my-agents
cd my-agentsThis creates the project structure with an agents/ folder and a sample agent configuration.
Define Your Agent
Edit the agent YAML file to configure your agent.
# agents/assistant.yaml
name: assistant
model: gemini/gemini-2.5-flash
description: "A helpful assistant"
system_prompt: |
You are a helpful assistant. Answer questions
clearly and concisely.
temperature: 0.7
max_concurrent_runs: 5Each YAML file in the agents/ folder defines one agent. You can have multiple agents in a single project.
Push to Deploy
Commit and push your changes to trigger a deployment.
git add .
git commit -m "Initial agent setup"
git push origin mainGo to your project in the Connic dashboard and click Deploy. Connic will build and deploy your agents automatically.
Create a Connector
To trigger your agent, create a connector from the marketplace. For example, you can create an HTTP webhook to trigger agents via API calls.
Go to your project's Connectors tab
Click Browse Marketplace and choose a connector type
Configure the connector (name, mode, etc.)
Open the connector and Link your agent to it
Test Your Agent
Trigger your agent using the connector you created. For example, if you created an HTTP webhook connector, you can trigger it with a curl command:
curl -X POST <webhook-url> \
-H "Content-Type: application/json" \
-H "X-Connic-Secret: <your-secret-key>" \
-d '{"message": "Hello, agent!"}'Check the Runs section in your project to see the agent's response and trace details.
You're all set!
Your agent is now deployed and ready to use.