Frequently asked questions about MAGIC#
What is MAGIC?#
MAGIC (standing for Multi-Agent Generative Investment Copilots) is our user-friendly, AI-driven tool, designed to expertly answer any financial question you throw at it.
It comprises a collaborative team of expert AI agents powered by large language models. Each agent is purpose-built to perform a particular task in financial research and analysis, meaning MAGIC can autonomously write code, use Python tools, call external APIs, or access public and private datasets on your behalf.
Best of all, you don’t need any coding knowledge to use MAGIC. All you need to do is enter a prompt–for example, “Give me the most popular finance news today”, “Show me Bitcoin returns since 2019”, or “Can you plot US GDP YoY over the past 5 years?”–and MAGIC will handle the rest.
What agents make up MAGIC?#
MAGIC consists of multiple autonomous agents acting as AI experts. Each one plays a specialized role, carrying out specific tasks and working in collaboration to best answer your prompt. Here are some of the standard agents:
Planner (hidden agent): The project manager of the pack, it works behind the scenes to create a comprehensive plan that addresses your prompt and delegates tasks to different agents.
Internet Browser: Efficiently scours the web for information, analyzes the retrieved content, and identifies key points.
SigTech Quant: Performs financial quantitative analysis across asset classes by retrieving financial market data, creating strategies, and using trade simulation tools for backtesting—as well as generating financial charts and reports, all using SigTech’s framework.
SigTech Copilot: Acts as your ‘no-code’ helper, retrieving documentation and Python code from SigTech’s knowledge base to help you handle data and build strategies within the SigTech platform.
Fed Analyst: Has access to the Federal Reserve FOMC documents.
You can pick and choose which agents to use, as long as you have at least one active agent in your conversation. Read our MAGIC user guide for more information on how to configure the agents.
As we continue to develop MAGIC, we plan to add more agents with specialist functionalities, as well as build on existing agents’ capabilities. Please note that access to particular agents can vary between users and organizations.
How does MAGIC work?#
Here’s how we’ve built each AI-powered agent:
First, we construct custom benchmarks to measure and optimize performance for example tasks in financial domains.
We engineer specialist knowledge and tools for the agent, enabling it to operate autonomously.
We augment the LLM with prompt engineering, adjusting its contextual information and fine-tuning behavior to enhance agent performance even further.
Finally, we adjust wider system processes within MAGIC to improve interactions with other agents.
How fast does MAGIC work?#
From receiving your prompt to coming up with a complex and detailed answer, MAGIC works in a matter of seconds. Your team of AI agents work collaboratively, carrying out their tasks to produce a solution to your query.
The planning and reviewing process is slightly slower than direct language model queries. However, this systematic process enhances the quality of MAGIC’s response.
Like working with a junior quant researcher, MAGIC won’t always get things right on the first go. But with MAGIC, it’s much faster to go back to your agents and ask them to redo or refine something.
How reliable is MAGIC?#
MAGIC can be incredibly helpful in providing insights, ideas, and information. We ground the response with data provided external to the models to increase the reliability. However, as with any AI tool, you should take the results as guidance only and always exercise your independent judgment.
If you want to see the code behind how MAGIC has reached a decision, you can view it in the Actions section of the interface.
Please refer to our terms and conditions for more information.
What can I use MAGIC for?#
MAGIC can be used for anything related to finance, such as data analysis, strategy development, real-time insights, and more.
You can use MAGIC to ask for financial insights, track the historical performance of a single stock, give an update on the latest financial news, analyze current macroeconomic factors, or even help with using SigTech’s platform.
Whether you’re a financial journalist, portfolio manager, quantitative analyst, independent investor, or simply someone who’s interested in finance, MAGIC can help get the answers you’re looking for.
Where does MAGIC source information from?#
As each agent has a particular role, MAGIC retrieves information and data from a variety of sources, including:
The Internet: The output will always include links to the web sources used by the Internet Browser agent.
SigTech’s knowledge base: The Copilot agent is designed to help you use the SigTech platform, meaning it uses SigTech’s Python framework to handle financial instruments, data, and strategy simulations. Read our SigTech Platform user guide to see what it can deal with.
SigTech’s datasets: The Quant agent uses validated datasets available in the SigTech platform.
External services: MAGIC can make API calls to certain external analytical services for extra calculations and data.
As with any AI language model, MAGIC’s output is based on the information and data provided, which may contain inaccuracies or biases. While we always strive for reliable and high-quality content, you should independently cross-reference information. Please refer to our terms and conditions for more details.
Can I access previous chat history with MAGIC?#
Yes–your past prompts and MAGIC’s answers are all saved, which you can easily access in the Topics sidebar in the platform. Right now, there’s no limit to how many chats can be saved.
However, we do have a certain time limit for storing images and data. For instance, graphs are currently stored for one month; once that’s up, it’ll be archived. If you want to retrieve it, you’ll need to run the prompt again.
Can MAGIC integrate with SigTech’s existing systems and data sources?#
MAGIC uses the SigTech Framework API to retrieve the same data as SigTech Enterprise, which we have cleaned and validated.
If you’ve used MAGIC to produce a strategy or portfolio, we don’t currently offer a way to automatically deploy that on the SigTech platform. However, it’s easy to copy any generated code into your research environment.
You can also export your chats in Jupyter Notebook format, download it as JSON data, or share with others via URL.
How does MAGIC differ from other AI tools available in the market?#
Compared with other AI tools, MAGIC stands out with its specialist knowledge and data, high-quality quantitative insights, use of credible sources, and data-powered analysis. Each agent is specially built to deal with a particular aspect of financial research and analysis, making MAGIC an ideal tool for financial and economic professionals.
The MAGIC workflow is designed to enhance reliability, with tasks delegated to specialist agents to produce grounded, well-rounded results. While other LLMs are geared towards instant answers to quick queries, MAGIC is developed to facilitate complex problem-solving on a larger scale.
Is MAGIC free to use?#
For now, yes. Free beta testing will be available in August and September.
Does MAGIC have any message limits?#
While using the MAGIC beta version, you will receive a set allowance of daily credits to use. During the beta testing period, 1 credit = 1 query to MAGIC. Your credits will be refreshed every day following UTC time.
Please note that your credit allowance and usage may change once the beta trial is over.
Will my data be visible to other users?#
No, your data will not be shared with other users. Any data you’ve entered, as well as the resulting MAGIC output, will remain only visible to you within the MAGIC platform.
Where can I get help with MAGIC?#
If you have a particular question you’d like help with, get in touch with your technical account manager or contact support@sigtech.com. You can also refer to our Getting started guide for an overview of how to use the tool.
Can I give feedback about MAGIC?#
Yes, we’re always open to feedback and suggestions on how to improve MAGIC. If you’re not satisfied with an answer, use the ‘Thumbs down’ button at the end—we’ll take this on board as we continue to enhance MAGIC and improve the user experience.
For all other feedback and comments, get in touch at magic@sigtech.com.