path·ai
curated paths through ai/ml
path·ai turns any ai/ml topic into an ordered path of modules. Pick a curated focus — computer vision, nlp, generative ai, reinforcement learning — or type any topic, and you get a sequence that builds on itself instead of a pile of bookmarks.
Every module pairs the best thing to read or watch with code you can run, then a short checkpoint. Generated paths are grounded in live web search so the links stay current. Free, no account.
← choose a different focus
computer vision fundamentals
a practical route from your first image classifier to modern detection, segmentation, and transformers — with code you can run today.
4 modules · 8 curated resources · checkpoint per module
learn
build
how it works
- 01
pick a focus
Choose a curated track or type any ai/ml topic.
- 02
get your path
Get ordered modules, each with a resource and runnable code.
- 03
learn it, prove it
Work through the code and pass each module's checkpoint.
a look inside
a few of the screens you'll actually use.
- ordered learning paths
- best resource + runnable code
- free · no account
generate
what do you want to learn?
pick one sub-field to start. you'll get an ordered path of modules — each with the best resource and runnable code.
fresh paths are built with live web search, so links stay current.
or start with a curated path
computer vision
teach machines to see
nlp & the transformer
language, end to end
generative ai
models that create
reinforcement learning
learning by doing
your ai/ml research navigator
cut through the noise. find your path.
the research landscape moves fast. path·ai gives you an ordered route through any ai/ml topic — best resource and runnable code, in order.
free · no account · 4 curated paths and counting
how it works
pick a focus
computer vision, nlp, generative ai, or rl.
get a curated path
ordered modules, each with a resource + code.
learn it, prove it
run the code, pass the checkpoint.
path·ai guides
Ways to use path·ai, and how it compares.
- comparisonA machine learning roadmap that actually links the resources — in orderMost ML roadmaps are a map of topics you still have to resource and sequence yourself. path·ai turns the roadmap into an ordered path where every step links the best resource and runnable code, free, no account.
- how toHow to learn machine learning for free, in the right order, with code at every stepYou don't need a paid course to learn machine learning — you need an order to follow and code to build. Here's a free, step-by-step way to learn ML using path·ai's ordered paths.
- how toWhat order should you learn machine learning in?The order is the part nobody tells you. Here's a sensible sequence for learning machine learning — from Python and math to classic ML, deep learning, and a specialisation — and how path·ai encodes it for you.
- use caseHow to learn LLMs and transformers without skipping the foundationsJumping straight to prompt engineering skips the part that makes LLMs make sense. path·ai gives you an ordered path through tokens, embeddings, attention, transformers, and fine-tuning, each step with a resource and runnable code.
- use caseLearn AI for free — no account, no paywall, just an ordered pathYou can learn AI to a high level without paying, because the best resources are already free. path·ai gives you a free, no-account path that orders those resources and adds runnable code and checkpoints.
- comparisonpath·ai vs roadmap.sh: a topic graph or an ordered, resource-linked path?roadmap.sh is a brilliant map of what to learn. path·ai turns each node into an ordered module with a linked resource, runnable code, and a checkpoint. Here's how they differ and when to use each.