Roadmaps

Live now

0%AI AgentsSoftware that reasons, calls tools, and acts on its own, instead of a model that only answers one prompt. Thirty-three lessons from the agent loop through tools, memory, multi-agent architectures and the frameworks used to ship them, to evaluating and deploying agents safely.Intermediate · 33 lessons · 749 min
0%AI EngineerBuilding products on top of models you did not train. Thirty-six lessons from what a token is through retrieval, agents, evaluation and safety, to the work of keeping an LLM feature alive in production.Intermediate · 36 lessons · 571 min
0%AI Red TeamingFinding the ways a model, its prompts, and the systems around it can be broken — before someone else does. Twenty-four lessons from prompt injection and jailbreaks through model extraction, poisoning, and agentic exploits, to the testing methodology and defenses a real engagement runs on.Advanced · 24 lessons · 548 min
0%Inference EngineeringRunning a trained model efficiently in production, not training one. Thirty-two lessons from latency and throughput through hardware, serving software and the techniques that speed generation up, to running it all at scale.Advanced · 32 lessons · 983 min
0%Machine LearningBuilding and training models from data, not calling ones someone else trained. Thirty-three lessons from what learning from data means through classical models, evaluation and neural networks, to where deep learning picks up.Intermediate · 33 lessons · 429 min
0%MLOpsTaking a trained model from a notebook to something that keeps running in production: versioning data, tracking experiments, building the pipelines that retrain and redeploy it, and watching it once it is live.Intermediate · 32 lessons · 599 min
0%Prompt EngineeringMaster the art and science of crafting effective prompts for large language models. From basics to advanced techniques, learn how to communicate with LLMs to get reliable, structured outputs at scale.Beginner · 29 lessons · 319 min

In preview

Engine previewPreviewA ten-node roadmap that exercises the graph, the path, progress, bookmarks and timestamped notes end to end. The structure is ours; the videos are well-known public explainers rather than picks from the Phase 4 sourcing protocol.10 lessons · 167 min

A preview is the engine, not the curriculum: real structure, real lessons and real progress, but videos that have not been through the sourcing review a shipped roadmap goes through. A preview is not counted as live, and search engines are told not to index it.

Wave 1AI & machine learning

Where Upshard starts, and where demand is highest right now.

Roadmap	Level	Topics	Lessons ready
AI EngineerPilot	Intermediate	36	36
Machine Learning	Intermediate	33	33
Inference Engineering	Advanced	32	32
AI Agents	Intermediate	33	33
AI Red Teaming	Advanced	24	24
MLOps	Intermediate	32	32
AI Product Builder	Beginner	53	0
Prompt Engineering	Beginner	29	29
AI Data Scientist	Beginner	9	0

Wave 2CS foundations & interview prep

Evergreen, and the backbone every other track links into.

Roadmap	Level	Topics
Computer Science	Beginner	241
Data Structures & Algorithms	Intermediate	161
System Design	Advanced	135
Software Architect	Advanced	115
API Design	Intermediate	93

Wave 3Web development

The largest audience, and the easiest place to find good free teaching.

Roadmap	Level	Topics
Frontend	Beginner	182
Backend	Intermediate	199
JavaScript	Beginner	116
TypeScript	Intermediate	88
React	Intermediate	71

Topic counts are the public estimates the waves were sized from. A roadmap we have designed reports its own node count instead, which is deliberately the smaller number: we merge the trivia and keep the lessons worth a video.

The full ranked catalog — 95 roadmaps, around 11,000 topics — lives in ROADMAP-CATALOG.md. Want one pulled forward? Open an issue and say why.

Save your progress

Your account

Delete your account?