Pick one skill.
Drill it until it’s yours.
Challenges build a whole project; practice sharpens a single skill. Each one is ten bite-size tasks that climb from easy to advanced — real Python, real models, instant feedback, all in your browser.
Python
Ten reps that take you from variables and loops to comprehensions, generators, and decorators — the Python every ML engineer leans on daily.
NumPy
Vectors, matrices, broadcasting, and the math that powers every model. Stop writing loops — start thinking in arrays.
Pandas
Load, filter, group, and reshape tabular data — the daily grind of every data and ML project, drilled until it's muscle memory.
Data Visualization
Turn numbers into pictures with matplotlib — line, scatter, bar, histogram, and the touches that make a chart actually readable.
Git & Version Control
Branch, commit, merge, and recover — the version control every developer lives in, drilled until it’s second nature.
Command Line
Navigate, pipe, and script from the shell — the fastest interface to your machine, one rep at a time.
Regular Expressions
The pattern-matching mini-language hiding inside every editor and language — finally make regex click.
Unit Testing
Write tests that catch bugs before your users do — assertions, fixtures, and mocking with pytest.
Type Hints
Annotate your Python so tools and teammates know what you meant — and let mypy find mistakes for you.
Object-Oriented Python
Classes, inheritance, and dunder methods — structure bigger programs the way real libraries do.
Data Cleaning
Real data is dirty — missing values, wrong types, duplicates, outliers. Drill the moves that make it usable.
Dates & Times
Parsing, time zones, and date math — the deceptively tricky skill behind every time-aware dataset.
APIs & HTTP
Fetch and send data over HTTP — query params, headers, auth, and error handling with requests.
Web Scraping
Pull structured data out of HTML — fetch, parse, and select elements without breaking the site’s rules.
JSON & File I/O
Move data in and out of files — JSON, CSV, nested structures, and large files that won’t fit in memory.
Regression
Fit lines and curves to data and measure the error — linear, polynomial, and regularised models on real datasets.
Classification
Tell classes apart — logistic regression, trees, KNN — and learn the metrics that tell you whether your model is actually any good.
Clustering
Group data with no labels at all — K-Means, the elbow method, and dimensionality reduction with PCA.
Feature Engineering
The work that moves the needle more than the model: encoding, scaling, binning, interactions, and leak-free pipelines.
Deep Learning
Build the network from first principles in NumPy — neurons, activations, forward pass, backprop, and gradient descent. The intuition every framework hides.
Model Metrics
Accuracy lies. Drill precision, recall, F1, ROC-AUC, and the regression metrics that tell the real story.
Cross-Validation
Stop trusting a single lucky split — k-fold, stratification, and leak-free validation you can rely on.
Hyperparameter Tuning
Find the settings that make a model sing — grid search, random search, and validation curves, without overfitting the search.
ML Pipelines
Chain preprocessing and models into a single, leak-proof pipeline you can cross-validate, save, and ship.
Linear Algebra
Vectors, matrices, and dot products — the math under every model, drilled with hands-on NumPy.
LLM Apps
The patterns behind every AI app — prompt templates, chaining, structured output, retrieval, and tool-using agents — wired to a real, live model. No keys, no setup.
Tokenization
Tokens are the atoms of every LLM — split text, count tokens, and decode IDs to demystify context limits and cost.
Function Calling
Let an LLM call your code — define tools, parse the call, run it, and return results in a clean loop.
Vector Search
Store embeddings and find the nearest ones — cosine similarity, indexes, and the engine behind RAG.
Chatbot Memory
Turn a one-shot model into a real conversation — manage history, trim context, and summarise memory.
Want a skill that isn’t here yet?
Tell us what you want to practice next. We add skills and tasks all the time — your request helps decide what’s next.