Skip to main content
Connic

Connic Documentation

Build, evaluate, deploy, and operate AI agents with the Composer SDK and Connic platform. Start with the task in front of you, then use the reference pages when you need exact configuration.

Last updated
On this page

Ready to deploy your first agent?

Create a project, connect a repo, and follow the quickstart with the dashboard open beside you.

Start free

Start with your current task

Each route starts with a working workflow and links to the relevant configuration reference.

Build your first agent

Create a project, define an agent, deploy it, and trigger the first run

Evaluate agent behavior

Write YAML tests for outputs and tool calls before deployment

Deploy with test gates

Map environments to branches, run tests, activate versions, and roll back

Operate production runs

Inspect inputs, outputs, traces, logs, latency, and usage

Use Connic with your AI toolsPlugin, skill, and MCP setup

Install the Connic plugin in a compatible coding agent to add the Connic authoring skill and authenticated, permission-scoped MCP connection together. Then describe what you want to build and let the agent work with your Connic project.

Plugin formats and installation steps vary by client. Follow the AI agent setup guide for verified plugin instructions and the separate skill and MCP path for other compatible clients.

How Connic Works

Connic is a platform for building and deploying AI agents. Here's how the pieces fit together.

Your Code

Agent Configuration + Python Tools

→

Connic Composer SDK

Validates & packages agents

↓
Connic

Connic Platform

Deploys, runs, and monitors your agents

Deployments

Automated builds

Execution

Scalable processing

Observability

Runs & traces

↓

Connectors

Bridge between agents and the outside world

Inbound

Trigger agents

Outbound

Deliver results

Sync

Request-response

Key Concepts

  1. Build

    Projects & environments
    A project is the top-level container for agents and platform settings. Use environments to isolate variables, connectors, deployments, retrieval and database data, and run history across development, staging, and production.
    Agents
    Define agents in YAML as LLM, sequential, or deterministic tool agents, then compose them when a workflow needs multiple steps.
    Tools
    Add tools to an agent with built-in tools, typed Python functions, MCP servers, or OpenAPI specifications.

  2. Ship

    Tests & deployments
    Write repeatable YAML tests against the deployed agent behavior and use them to gate deployments. Deploy from a mapped Git branch or the CLI; successful versions remain available for rollback.
    Connectors
    Configure inbound connectors to trigger agents; outbound connectors deliver results, and sync connectors wait for a response. Connector configuration stays isolated by environment.
    REST API
    Use project-scoped API keys to manage and observe platform resources. When an external system needs to start an agent, use a connector.

  3. Operate

    Runs & traces
    Every execution becomes a run. Inspect its input, output, context, logs, and trace, then review usage by agent and model.
    Retrieval & database
    Search documents with Retrieval; store schemaless application state in the database. Both remain isolated by environment.
    Safety & quality
    Inspect inputs and outputs with guardrails; pause sensitive tool calls for approval; score selected runs with judges; and compare live variants with A/B tests.
Quick StartCreate and deploy your first agent
terminal
# Install the SDK
pip install connic-composer-sdk

# Create a new project
connic init my-agents
cd my-agents

# Push to your connected repo to deploy
git push origin <branch>
Read the full guide

Choose your next step

Quickstart

Create, deploy, and trigger your first agent

Migrate from LangChain

Bring an existing LangChain or LangGraph app into Connic

Migrate from ADK

Bring an existing Google ADK project into Connic

Agent Configuration

Learn how to configure LLM, Sequential, and Tool agents