book
Checkout our new book! Hands on AI Trading with Python, QuantConnect, and AWS Learn More arrow

AI Assistance

Getting Started

Introduction

We are deeply integrating AI into our core product to make designing algorithms on QuantConnect as easy as possible. Most clients will experience the benefits of this without realizing it, as our platform quietly solves issues. If you'd prefer a more hands-on approach or a local LLM integration, you can harness some of the new tools we publish to make this easier—such as our chatbots, agents, and an MCP server.

QuantConnect Chatbot

Our chatbot, Mia, is a peer programmer you can use to help you write and debug project code. She is aware of the ensure project's context, QuantConnect documentation, runtime errors, and logs. She uses a proprietary blend of commercial and open-source models to accomplish the goals you set.

We encourage using Mia before other commercially available LLMs. Our benchmarks show Mia is able to generate working QuantConnect code in 75% of test cases vs OpenAI o3 25%. For more information, see Mia Chatbot.

QuantConnect MCP Server

The QuantConnect MCP server is a bridge for AIs to interact with our cloud platform. This server equips the LLM with tools to create projects, run backtests, deploy live algorithms, and more. For more information, see MCP Server.

QuantConnect Agents

Coming later in 2025 we will deploy fully automated AI to perform the quant research process (agentic quant research). These agents will be available for all QuantConnect clients and reduce or eliminate the need to learn our API.

You can also see our Videos. You can also get in touch with us via Discord.

Did you find this page helpful?

Contribute to the documentation: