→ AI-Guided Learning Platform

Learn by
Building
Real Projects.

Not a course. Not a tutorial.
Everything you need — in one place, ready to go. Open a project, start building. Your AI tutor teaches you to think, not just to code.

How it works ▶
Step 3 of 8  ·  38%
notebook.ipynb
Step 3 — Exploratory Data Analysis
Understand the data before touching a model. Spot problems early.
[1]
import pandas as pd import numpy as np # Load gene expression dataset df = pd.read_csv('gene_expression.csv') print(df.shape) print(df['subtype'].value_counts())
Out [1]
(523, 1842)
subtype
0    441  ← 84.3%
1     58  ← 11.1%
2     24  ← 4.6%
[2]
# Check missingness & feature ranges missing = df.isnull().sum().sum() print(f"Missing: {missing}") summary = df.describe().loc[[ 'mean', 'std', 'min', 'max' ]].round(3)
Out [2]
Missing: 0
       gene_0001  gene_0002
mean     0.002     0.114
std      2.841     2.903
min     -4.231   -3.981
max     12.340   11.883
[ ]
# Your next analysis here...
# What should you look at next?
Klerisy Tutor
Gene Expression Classification
Klerisy
Good. 523 samples, 1,842 features. What does that ratio immediately suggest?
You
p ≫ n — curse of dimensionality?
Klerisy
Exactly. What technique addresses that before you model?
Think about what PCA does to the feature space.
You
Dimensionality reduction first — PCA to compress the 1,842?
Klerisy
Right. Now — subtype 0 is 84% of the data. What metric should you not use, and why does it fool most beginners?
↑

The hardest part isn't the maths, the models, or the code. It's finding a place to start that doesn't make you feel like you're already behind. Klerisy is that place.

How it works

Zero setup.
Real work. Actual thinking.

Every project comes fully loaded — data, environment, and an AI guide that asks questions instead of giving answers.

Step 01
Pick a project in your field

Biology, finance, clinical data, operations. Choose a domain you already know — the data science will feel immediately relevant, not abstract.

No DS experience needed
Step 02
Everything is already set up

Python, Jupyter, every library — running in your browser. No installs, no environment errors, no Stack Overflow rabbit holes. Open and code.

Browser-based · instant start
Step 03
Your AI guide thinks with you

Stuck? It doesn't hand you the answer — it asks you the right question. You understand every line you write and every decision you make.

Socratic AI tutor
Heard these before?

Every reason you've been
putting it off — handled.

I don't know where to start.
You don't have to. Pick a project in your domain and Klerisy walks you through every step — from raw data to final interpretation. You just show up.
I'm not a programmer.
Neither were most of our learners when they started. You'll write real Python — with an AI alongside you that explains every concept the moment it comes up.
I've tried courses before and gave up.
Courses teach theory in a vacuum. Klerisy puts you inside a real project from day one. The context makes everything stick in a way lectures never do.
I don't have time to set everything up.
There's nothing to set up. Open your browser, click a project, start building. The full Python environment is ready in under 10 seconds — every time.
Who it's for

Wherever you're starting from,
you belong here.

No prerequisites. No ideal background. Klerisy meets you where you are — with a real project in a domain you care about and an AI guide that never lets you get lost.

The new graduate
"I can write the code. I just freeze when the data gets messy."

You've done the coursework. You know the algorithms in theory. But real data doesn't look like a clean CSV — and nobody taught you how to make judgment calls under ambiguity. That's exactly the gap Klerisy closes.

→ 3 projects you can speak to deeply in any interview
The domain expert
"I have years of data sitting there. I just can't do anything with it."

You're a researcher, clinician, analyst, or engineer who understands your field better than most. You don't need to learn data science from scratch — you need a path that starts from where you already are.

→ Run your own analysis on your own data within weeks
The career changer
"I've started three courses. I've finished zero."

Courses lose you because they start with theory, not work. Klerisy starts with a real project — in a domain you actually care about — and lets the concepts emerge as you need them. It's a completely different experience.

→ A real portfolio, not a shelf of certificates nobody asked for

Whichever one you are — your first project is waiting.

Project library

Real problems.
Real domains. Real thinking.

Each project teaches a specific thinking trap that senior data scientists learn to spot. Everything is set up — just open and start.

Biology · Genomics
Gene Expression & Cancer Subtype Classification
You're given RNA-seq data from 500 tumor samples. Your job is to identify subtypes — but the data will challenge everything you think you know about classification.
Imbalanced classes Dimensionality reduction Statistical testing Clustering
Intermediate 8–12 hrs
→
Clinical · Epidemiology
ICU Readmission Prediction with Missing Data
A clinical dataset with 35% missingness. Before you can model anything, you need to make decisions that will change your results — and understand why.
Missing data strategies Data leakage Survival analysis
Advanced 12–18 hrs
→
Finance · Risk
Credit Default Modeling When the Past Doesn't Predict the Future
Historical credit data trained beautifully. Then the economic regime changed. Learn what distribution shift is, how to detect it, and why your 96% accuracy is lying to you.
Distribution shift Model calibration Uncertainty quantification
Advanced 10–16 hrs
→
Operations · Supply Chain
Demand Forecasting in a World of Outliers
Sales data with COVID-era anomalies baked in. A naive model will look great. A thoughtful model will force you to ask: what am I actually trying to predict?
Outlier treatment Time series Baseline modeling
Beginner 5–8 hrs
→
Social Science · Policy
Causal Inference in Education Interventions
Does the tutoring program actually work? Or does selection bias make it look that way? Learn the difference between correlation, causation, and confounding at a fundamental level.
Causal inference Selection bias Propensity scoring
Intermediate 8–12 hrs
→
Biology · Ecology
Species Distribution Modeling with Spatial Autocorrelation
Your training data isn't independent. The samples are geographically clustered. A standard train/test split will give you inflated confidence — and you need to catch it.
Spatial data Autocorrelation Cross-validation strategy
Intermediate 8–14 hrs
→

Showing 6 of 24 projects. Join the waitlist for full access to every domain.

Pricing

Invest in judgment.
Not just another subscription.

Two tiers built around real learning outcomes — not feature counts. Early access pricing locked for waitlist members.

Starter
$200
one-time · 3 months access
For domain experts taking their first serious step into data.
5 projects (your choice of domain)
Full AI Socratic tutor — unlimited messages
Browser-based Python/Jupyter environment
Structured step-by-step guidance
Project completion certificate
Email support
Full Access
$500
one-time · 12 months access
For serious learners building a full data science capability.
All 24 projects — every domain
Full AI tutor — unlimited, always on
Early access to new projects as they launch
GitHub portfolio integration
Priority support + community access
All future projects included for 12 months
Teams
Custom
per seat · annual billing
For research labs, data teams, and graduate programs.
Everything in Full Access
Admin dashboard & cohort tracking
Custom domain-specific project creation
Team progress reporting
Dedicated onboarding call
SLA & invoiced billing available
Enterprise
White-labeled deployments, API access, custom integrations, and volume licensing for institutions and large organisations.
Early access

Your first project
is one click away.

Join the waitlist. Get early access pricing, first pick of projects, and an AI tutor that's ready the moment you are.

247 people already on the waitlist
No credit card required · Early access pricing locked in · Unsubscribe anytime
You're on the list.
We'll reach out when your spot is ready — with early access pricing locked in.
In the meantime, tell one colleague who's been meaning to do this too.