Research education · Quantic Eagle operates only with its own capital. No client funds, investment advice or trading signals.

IN PREPARATION · FREE RESOURCES AVAILABLE NOW

Before Capital / Trading system design with AI

A decade in the lab.
Design your next
trading system.

Lessons from a working research lab, the choices behind the models and practical knowledge earned through experience. Learn to structure your research, from the first idea and its data to model comparisons, risk and the AI agents helping you build.

Notify me when it is ready See what you will learn Inside the research lab

A practical fieldbook with twenty chapters, six workshops, visual explanations, twelve worksheets and seven Python tools. Study the experience, adapt the procedures and develop your own research project.

Where are you starting from?

A practical fieldbook for people developing a quantitative project who already know the basic ideas of backtesting, risk and return.

You are designing your first system

You know the trading basics and want to organise the idea, data, comparisons and AI work before adding more code.

You already have a backtest or pipeline

You want to make better research decisions, compare models consistently and identify which parts of the process deserve more work.

You work independently or in a small team

You want to give AI agents precise assignments, make experiments reusable and measure the time, cost and quality of completed work.

To read the fieldbook, you need a browser and familiarity with the basic concepts. For the Python exercises, you need to work with CSV files and use a terminal. If backtests, drawdown or training data are new to you, introductory study should come first.

Give your idea a structure.

Six decisions that shape a trading system. Each connects a design choice to a worksheet, a case study or an exercise in the fieldbook.

A map of the design process. Arrows show the working sequence; an experiment may send you back to an earlier decision.

The idea

Turn an intuition into a precise question and choose a reference against which to measure progress. Chapter 01 and worksheet 01.

The data

Define which information the system can use, for which instruments and at what time. Chapters 02–03 and worksheets 02–03.

The models

Compare alternatives on consistent terms and examine what an additional layer contributes. Chapters 04, 07 and 13.

The risk

Design how you will measure risk along the path and connect results to the decisions that produced them. Chapters 05 and 11, equity lab.

The AI agents

Set bounded assignments, check the work delivered and measure the cost of completed tasks. Chapters 08, 15 and 20, workshop 26.

The next experiment

Bring your decisions together in a dossier and decide what to observe before the next stage. Chapters 10 and 19, sample dossier.

The work between the theory and a functioning lab.

The distinctive material is a selection of cases, decisions and practices drawn from internal research: useful experiments, abandoned approaches, corrections and findings that changed the design. The fieldbook explains the transferable reasoning and gives you ways to practise it.

Aspect	Introductory study	This fieldbook
Starting question	How does this concept work?	How do I turn it into a decision in my project?
Core material	Foundations, definitions and basic exercises.	Lab cases, decisions with their rationale and teaching reconstructions.
Work produced	An understanding of the language and tools.	Worksheets, experiments, agent assignments and a project dossier.
Using AI	Learning tools and techniques.	Defining tasks, inputs, checks, costs and responsibilities in day-to-day work.

An illustrated HTML fieldbook, workshops, worksheets and local software. Foundational study and this lab work serve complementary purposes; the fieldbook does not teach mathematics, Python and market mechanics from scratch.

Three assumptions worth testing.

A better metric should pick the better model.

In the internal comparison of 192 candidates, the proxy and economic ranking told different stories. The case connects selection criteria to the actual research objective.

Another layer should make the system stronger.

The fieldbook shows how to measure the added contribution under consistent conditions. The value of complexity becomes an experimental question.

Matching predictions should produce matching trades.

The decision-trace case shows how selection, constraints and sizing can change what happens after the score.

Each case states its scope. Teaching reconstructions are distinguished from internal observations; the lessons are not presented as universal laws of markets.

See the reasoning at work.

Three interactive cases show why these design choices matter. Open a case, change one condition and watch what follows.

01 / EXHIBIT

Same scores. Different decisions.

A complete trace identifies the first divergent field: selected. After correction, the declared traces match within their limited scope.

02 / EXHIBIT

Every batch returns a response. The same objects appear twice.

Each request is assigned an explicit subset. The check looks for repeated assignments, responses outside their request, duplicates and omissions.

03 / EXHIBIT

The feature is a number. Its window is incomplete.

The expected observations come from the declared calendar. The check finds missing observations, nulls and data available only after the decision.

The False Green Museum Open a sample dossier

A method you can put to work.

Seven Python commands: equity · temporal · folds · ranks · trace · batches · windows
Practical workshops: 6 · Field guide chapters: 20
Open a sample dossier · Printable HTML
Agent templates in your chosen language: AGENTS.md / CLAUDE.md / .cursor/rules

The fieldbook teaches research design and verification. Developing your own system still requires data, implementation and experimentation; a broker-ready trading strategy is not included.

The decade refers to the founder’s research journey, which began before the company was formed. This edition draws selected lessons from that work; it is not a ten-year live performance record.

I only have a list of trades

A trade list does not contain the equity path or the provenance of your features. Read the observation workshop and prepare prospective collection in a demo environment.

I have an equity curve

Open the free mapper, confirm columns and cash flows, then use the checker. The measurement covers only available samples.

I am building a pipeline

Reproduce the three broken cases, then connect declared traces, batches and windows. Retain the inputs, receipts and dossier.

Open research desk

Read the research. Try the tools. Follow the fieldbook as it takes shape.

The article and browser tools below are free to use now. The complete fieldbook is in preparation; its final contents and any purchase terms will be published before orders open.

01
Inside the research lab
Six design decisions, practical lessons and the reasoning behind them.
02
Observed equity check
Measure drawdown from the observations in your CSV, with explicit limits.
03
Three interactive cases
Change one condition. Watch what the original check missed.
04
CSV column mapper
Choose your columns and formats explicitly. Keep your data in your browser.
05
A worked decision dossier
See how findings, supporting files and missing checks fit together.

Before you ask for an update

Is this a course for beginners?

It is an illustrated practical fieldbook with exercises and tools. You should already understand backtesting, risk and return. It does not start from basic mathematics or Python.

Can I buy or reserve it now?

No. We are sharing free resources while preparing the fieldbook. A notification request creates no order, deposit or reservation. Price and release date have not been announced.

Will it include Quantic Eagle’s trading strategies?

The material explains research methods, design choices and selected lessons from internal work. It does not include our proprietary alpha, trading signals, operational models or a promise of returns.

What does “a decade” refer to?

The founder’s research journey, which began before the company was formed. It is not the company’s age or a ten-year live trading record.

Which language will I receive?

Request the notification in English, Italian or Spanish. The planned delivery is one language per package; the final editions will be described before sales open.