hands-on AI labs

Build real AI projects in hands-on labs

The code, data and models are ready in your browser, and every step is checked as you go.

popular:

163 labs30 on real NVIDIA GPUs5 free

Where to start

Pick the line that sounds like you. Each one opens with a lab you can finish in one sitting.

new to AI

Call a model from Python, then build a chatbot and an assistant of your own.

Beginner · 40 minYour First AI Call: Talk to a Language Model from PythonIn browserfree Then the Start with AI track

building AI apps

Wire an agent to real tools and ground its answers in your own documents.

Intermediate · 80 minBuild an Agent From Scratch: The Tool Loop Without a FrameworkIn browserfree Then the AI agents and MCP track

running AI infrastructure

Schedule a GPU pod on your own Kubernetes cluster, then triage the pods that will not start.

Beginner · 5 minWelcome to NCA-AIIO Labs: Schedule Your First GPU PodKubernetesPro Then the GPU and Kubernetes track

securing AI

Break into a live RAG assistant with prompt injection, then build the guardrail that stops it.

Advanced · 75 minIndirect Prompt Injection: Exfiltrate Data from a RAG AssistantIn browserfree Then the AI security and red teaming track

Pick what you want to build

Each track runs from its first lab to its hardest, and every lab checks your work step by step.

Start with AI

21 labs · beginner · 1 free

Your first AI call, a chatbot, tested prompts and everyday automations. No machine learning background needed.See the track

Beginner · 40 minYour First AI Call: Talk to a Language Model from PythonIn browserfree

Beginner · 50 minLearn Python by Building a ChatbotIn browserPro

Beginner · 45 minTokens, Context and Cost: Measure Before You SpendIn browserPro

Beginner · 45 minPrompting That Passes Tests: Improve a Prompt with a Score, Not a HunchIn browserPro

Beginner · 60 minJudge the Output: Pick the Better Prompt with Numbers You Can DefendIn browserPro

Beginner · 40 minCompare AI Models Before You Trust One: Accuracy, Cost and a CascadeIn browserPro

Beginner · 50 minFiles and JSON with AI: Turn a Folder of Reviews into DataIn browserPro

Beginner · 60 minpandas + LLM on a Real CSV: Clean, Classify, Check, ReportIn browserPro

Beginner · 55 minStructured Output with Pydantic: Validate, Retry, GroundIn browserPro

Beginner · 50 minEmbeddings You Can See: Search, Map and Clean a Catalogue with VectorsIn browserPro

Beginner · 55 minCatch a Hallucination: Ground, Quote and Audit Every AnswerIn browserPro

Beginner · 60 minCall Web APIs Safely: Keys, Errors, Retries and Rate LimitsIn browserPro

Beginner · 45 minTerminal and Git for AI Work: Review and Undo What an AI Assistant ChangesIn browserPro

Beginner · 45 minEmail Triage with AI: Route an Inbox by What Mistakes CostIn browserPro

Beginner · 45 minMessy Documents to a Clean Table: Invoices into a Spreadsheet with AIIn browserPro

Beginner · 50 minClassify 500 Spreadsheet Rows with AI and Measure the Error RateIn browserPro

Beginner · 45 minMeeting Notes to Action Items with AI: Owners, Dates and Nothing InventedIn browserPro

Beginner · 50 minMulti-Step AI Workflow: Draft, Review and Revise Without CodeIn browserPro

Beginner · 45 minBuild a Prompt Template Library for Your TeamIn browserPro

Beginner · 50 minBuild Your Own AI Assistant: A System Prompt and a Knowledge File That Hold UpIn browserPro

Beginner · 50 minTrigger-Based AI Automation: Webhook Inbox, Drafted Replies and an Approval Step, Without CodeIn browserPro

AI agents and MCP

26 labs · beginner to advanced · 2 free

Tool loops, ReAct, MCP servers and clients, multi-agent supervisors and agent evaluation.See the track

Intermediate · 80 minBuild an Agent From Scratch: The Tool Loop Without a FrameworkIn browserfree

Intermediate · 35 minBuild a ReAct Agent with NVIDIA NIMIn browserPro

Intermediate · 35 minBuild an AI Agent 3 Ways: ReAct vs Tool Calling vs Plan-and-ExecuteIn browserPro

Intermediate · 30 minStructured Output & Function Calling with NIMIn browserPro

Intermediate · 50 minWeb Research Agent: Search, Read and Cite Without Being Fooled by the WebIn browserPro

Intermediate · 50 minCode-Executing Data Agent: Let an LLM Answer Questions With pandas, SafelyIn browserPro

Intermediate · 50 minText-to-SQL Agent: Answer Questions From a Database Without Letting the Model Touch the DataIn browserPro

Intermediate · 55 minSpec to Code: Build a Test-Driven Coding AgentIn browserPro

Intermediate · 50 minAI Code Review Bot: Parse a Diff, Find Bugs, Score and Gate the PRIn browserPro

Intermediate · 55 minRefactor Legacy Code Safely: Characterization Tests and an AI Refactoring AgentIn browserPro

Intermediate · 55 minDebug With an Agent: Reproduce, Fix, and Add the Regression TestIn browserPro

Intermediate · 35 minAdd Long-Term Memory to an AI Agent: LangGraph + MilvusIn browserPro

Advanced · 40 minBuild an MCP Tool Server & Connect a LangChain AgentIn browserPro

Intermediate · 60 minBuild an MCP Client and Host: Handshake, Tool Discovery, Error Handling and ApprovalsIn browserPro

Advanced · 40 minBuild Two Agents That Talk via the A2A ProtocolIn browserPro

Intermediate · 40 minBuild a Multi-Agent Supervisor with LangGraphIn browserPro

Intermediate · 60 minPlanner-Executor Agents with Self-Critique: Plans, Validators, Replanning and Stopping RulesIn browserPro

Intermediate · 60 minHuman-in-the-Loop Agent: Approval Interrupts, Durable Pauses, Crash-Safe Tools and EscalationIn browserPro

Intermediate · 30 minEvaluate an Agent with LLM-as-JudgeIn browserPro

Intermediate · 80 minEvaluate an AI Agent: Trajectories, Tool Calls and an LLM JudgeIn browserPro

Intermediate · 25 minModel Routing & Cost Cascade with NIMIn browserPro

Intermediate · 60 minOptimise Prompts with DSPy: Signatures, Metrics, Few-Shot Compilers and Held-Out TestsIn browserPro

Beginner · 45 minGate an Agent's Tool Calls with JevIn browserfree

Intermediate · 60 minRoute Between a Small and a Large Model with JevIn browserPro

Intermediate · 60 minCalibrate Jev's Probabilities and ThresholdsIn browserPro

Intermediate · 50 minFind Where Jev Fails Before Your Users DoIn browserPro

RAG and search

14 labs · intermediate to advanced · 1 free

Chunking, hybrid search and reranking, permission-aware retrieval, GraphRAG and RAG evaluation.See the track

Intermediate · 35 minBuild a RAG Pipeline with NVIDIA NIMIn browserfree

Intermediate · 45 minRetrieval-Augmented Generation (RAG) Pipeline with Local ModelsNVIDIA GPUPro

Intermediate · 50 minRAG Chunking Shoot-Out: Measure Which Chunking Strategy RetrievesIn browserPro

Intermediate · 55 minDocument AI: Turn PDFs, Tables and Scans into Clean RAG ChunksIn browserPro

Intermediate · 55 minHybrid Search and Reranking: BM25, Embeddings, RRF and an LLM RerankerIn browserPro

Advanced · 40 minAdvanced RAG: Hybrid Search + Cross-Encoder RerankingNVIDIA GPUPro

Intermediate · 50 minQuery Rewriting and HyDE: Better Queries for the Search You HaveIn browserPro

Intermediate · 55 minVector Index Internals: Exact Search, IVF, HNSW, Product Quantization and Filtered Search with FAISSIn browserPro

Intermediate · 60 minGraphRAG: Build a Knowledge Graph from a Wiki with an LLM and Answer Multi-Hop QuestionsIn browserPro

Intermediate · 35 minMultimodal RAG with NeMo RetrieverIn browserPro

Intermediate · 50 minEmbedding Recommender: More-Like-This, Offline Evaluation, Co-occurrence, Cold Start and MMRIn browserPro

Intermediate · 80 minEvaluate a RAG Pipeline: Retrieval Metrics, Faithfulness and a Regression GateIn browserPro

Intermediate · 50 minPermission-Aware RAG: Access Control, Metadata Filters and a Cache That Cannot LeakIn browserPro

Intermediate · 55 minLong Context vs RAG: Accuracy, Cost and Latency on the Same 24 QuestionsIn browserPro

Machine learning and deep learning

17 labs · beginner to intermediate

scikit-learn and PyTorch on real datasets, with the metrics and debugging that decide what ships.See the track

Beginner · 50 minYour First Machine Learning Model: Predict Churn with scikit-learnIn browserPro

Beginner · 45 minMetrics That Match the Business: Choose a Threshold from a Cost TableIn browserPro

Beginner · 50 minData Cleaning and Feature Engineering: Predict Rents From a Messy ExportIn browserPro

Intermediate · 45 minOverfitting and Cross-Validation: Find What Really Makes a Better CupIn browserPro

Intermediate · 50 minGradient Boosting with XGBoost: Predict Late Deliveries and Explain Every PredictionIn browserPro

Intermediate · 50 minCustomer Segmentation with k-means and PCA: Scaling, Choosing k, Stability and DeploymentIn browserPro

Intermediate · 50 minTime-Series Forecasting: Baselines, Backtesting, Calendar Features, Prediction Intervals and the Newsvendor RuleIn browserPro

Intermediate · 55 minImbalanced Data and Anomaly Detection: Average Precision, Rebalancing, Alert Budgets and Unseen FailuresIn browserPro

Intermediate · 50 minExplain a Model: Permutation Importance, Target Leakage, Partial Dependence and Exact Shapley ValuesIn browserPro

Intermediate · 60 minBuild a Recommender: Collaborative Filtering, Matrix Factorization and the Metrics That DisagreeIn browserPro

Beginner · 45 minPyTorch in 45 Minutes: Tensors, Autograd and Your First Training LoopIn browserPro

Beginner · 45 minA PyTorch Training Loop From Scratch: Datasets, Epochs, Evaluation and Early StoppingIn browserPro

Intermediate · 50 minDebug a PyTorch Training Run: NaN Loss, Broadcasting Bugs, Learning Rate and Data LeaksIn browserPro

Intermediate · 50 minImage Classification with Transfer Learning in PyTorch: From a Small CNN to a Fine-Tuned ResNetIn browserPro

Intermediate · 35 minVision-Language Models: Captioning and Visual QANVIDIA GPUPro

Intermediate · 30 minVisual Q&A with NVIDIA VLMsIn browserPro

Intermediate · 55 minReinforcement Learning Basics: Q-Learning and Reward Shaping on a GridworldIn browserPro

LLM training and fine-tuning

14 labs · beginner to advanced

LoRA and QLoRA fine-tuning, DPO alignment, and a tokenizer and tiny GPT built from scratch.See the track

Intermediate · 45 minFine-Tune an LLM with LoRA and QLoRA (Jupyter)NVIDIA GPUPro

Intermediate · 55 minFine-Tune a Small Text Classifier: Baselines, a Training Loop, Early Stopping, Abstention and a Shift TestIn browserPro

Intermediate · 40 minQuantize & Optimize LLMs with bitsandbytesNVIDIA GPUPro

Advanced · 55 minRLHF & DPO AlignmentNVIDIA GPUPro

Advanced · 45 minContinued Pre-Training: Adapt a Pretrained LM to a New DomainNVIDIA GPUPro

Advanced · 75 minTrain an Embedding Model: Contrastive Fine-Tuning for RetrievalIn browserPro

Intermediate · 45 minFine-Tune Stable Diffusion with LoRA: Custom Text-to-ImageNVIDIA GPUPro

Intermediate · 45 minData Preparation for LLM TrainingNVIDIA GPUPro

Intermediate · 50 minCurate a Fine-Tuning Dataset: Deduplicate, Filter, LLM-Judge and Balance Instruction DataIn browserPro

Intermediate · 40 minSynthetic Data Generation for Model TrainingNVIDIA GPUPro

Beginner · 45 minBuild a BPE Tokenizer From Scratch in Python (and See Why Some Languages Cost More)In browserPro

Intermediate · 50 minBuild a Tiny GPT From Scratch on a CPU: Attention, Transformer Blocks and Text GenerationIn browserPro

Advanced · 50 minBuild a Transformer from Scratch: Attention, Masking & LayerNormNVIDIA GPUPro

Advanced · 55 minTrain a Small Language Model from ScratchNVIDIA GPUPro

LLMOps and MLOps

22 labs · intermediate to advanced

vLLM serving, load tests against SLOs, tracing, drift monitoring and prompt tests in CI.See the track

Intermediate · 45 minDeploy & Serve LLMs in Production (Jupyter)NVIDIA GPUPro

Intermediate · 40 minInference Serving Patterns: Dynamic Batching, Throughput, and the Triton Mental ModelNVIDIA GPUPro

Advanced · 55 minvLLM Production Serving: PagedAttention, Continuous Batching, Prefix CachingNVIDIA GPUPro

Intermediate · 40 minBatch Size & Precision Sweep: Finding Your Sweet SpotNVIDIA GPUPro

Intermediate · 60 minServe an ML Model on CPU: ONNX Export, FastAPI, Dynamic Batching and a p95 Latency BudgetIn browserPro

Intermediate · 55 minShip an LLM Backend: FastAPI with API Keys, Rate Limits, Quotas, Streaming and Safe FailuresIn browserPro

Intermediate · 90 minBuild an LLM Gateway: One Door Between Your Apps and the ModelIn browserPro

Intermediate · 50 minStreaming and Prompt Caching: Time to First Token, SSE and Cheaper PromptsIn browserPro

Intermediate · 50 minContext Engineering: Token Budgets, Compaction and Running Notes for Long ChatsIn browserPro

Intermediate · 45 minEvaluation & Benchmarking LLMsNVIDIA GPUPro

Intermediate · 50 minPrompt Regression Testing in CI: A Golden Set That Blocks Bad Prompt ChangesIn browserPro

Intermediate · 50 minCI for Models: Data Contracts, Behavioral Tests, Golden Sets and a Merge GateIn browserPro

Intermediate · 45 minTraining Pipeline Orchestration: Ordering, Retries, Failure Isolation and ResumeIn browserPro

Intermediate · 45 minData and Model Versioning: Content Addressing, Lineage and Garbage CollectionIn browserPro

Intermediate · 60 minFeature Store Basics: Point-in-Time Correctness and Training-Serving SkewIn browserPro

Intermediate · 45 minPublish a Model: Card, Evaluation and a Versioned ReleaseIn browserPro

Intermediate · 35 minMLflow Experiment Tracking: From Single Run to Team WorkflowNVIDIA GPUPro

Intermediate · 40 minReproducible Training: The Flags, The Cost, The ArtifactsNVIDIA GPUPro

Intermediate · 50 minLLM Load Testing and SLOs: TTFT, TPOT, Open-Loop Traffic, Goodput and CapacityIn browserPro

Intermediate · 75 minLLM Observability: Trace, Cost and Debug a RAG AssistantIn browserPro

Intermediate · 50 minML Model Monitoring: Data Drift with PSI, Delayed Labels, Alert Rules and Root CauseIn browserPro

Intermediate · 45 minIncident Drill: Debug a Failing ML Service from Logs and MetricsIn browserPro

GPU and Kubernetes

20 labs · beginner to advanced

GPU scheduling on your own Kubernetes cluster, the GPU Operator, CUDA kernels and profiling.See the track

Beginner · 5 minWelcome to NCA-AIIO Labs: Schedule Your First GPU PodKubernetesPro

Intermediate · 40 minNVIDIA GPU Operator on k3s: Single-Node Kubernetes for GPU WorkloadsNVIDIA GPUPro

Intermediate · 35 minInside the NVIDIA GPU Operator: From Helm to Workload-ReadyKubernetesPro

Intermediate · 40 minKubernetes Resource Requests & Limits: Who Gets What, and Who SurvivesKubernetesPro

Intermediate · 35 minMulti-GPU-Type Targeting: nodeSelector, nodeAffinity & TolerationsKubernetesPro

Intermediate · 35 minPriorityClass & Preemption: Who Survives the GPU SqueezeKubernetesPro

Intermediate · 35 minWorkload Controllers: Deployment, StatefulSet, DaemonSet for AIKubernetesPro

Intermediate · 35 minPersistent Storage for AI Workloads: PVCs, StorageClass & the Checkpoint PatternKubernetesPro

Intermediate · 40 minGPU Container Lifecycle: Build, Test, Ship, RollbackNVIDIA GPUPro

Intermediate · 35 minRolling Updates, Rollback & Blue-Green for AI InferenceKubernetesPro

Intermediate · 40 minStuck-Pending Triage Day: Diagnose Any GPU Pod That Won't RunKubernetesPro

Intermediate · 40 minGPU Observability: From nvidia-smi to a Production Monitoring StackNVIDIA GPUPro

Advanced · 50 minGPU Health Checks + Auto-RemediationNVIDIA GPUPro

Advanced · 45 minCUDA Programming FundamentalsNVIDIA GPUPro

Intermediate · 35 minProfile PyTorch Training with the Built-in ProfilerNVIDIA GPUPro

Intermediate · 35 minNsight Systems Profiling: Finding the Bottleneck That Costs You 40% of Your GPUNVIDIA GPUPro

Advanced · 45 minGPU Sharing: Streams, MPS, MIG, and the Real Cost of ContentionNVIDIA GPUPro

Intermediate · 30 minNVIDIA DALI: GPU-Accelerated Data PipelinesNVIDIA GPUPro

Intermediate · 40 minGPU-Accelerated Data Science with RAPIDSNVIDIA GPUPro

Intermediate · 35 minGPU Cost & Efficiency AuditNVIDIA GPUPro

AI security and red teaming

29 labs · beginner to advanced · 1 free

Prompt injection, tool poisoning and data exfiltration against live targets, then the defenses.See the track

Intermediate · 50 minThreat-Model an LLM App: Derive OWASP LLM Threats from the Architecture, Rate Them, and Test the ModelIn browserPro

Beginner · 100 minRecon and Harness: Map a RAG Attack Surface and Measure Attack-Success-RateIn browserPro

Intermediate · 70 minSystem-Prompt Extraction: Recover a RAG Assistant's Hidden InstructionsIn browserPro

Intermediate · 75 minSensitive Data Disclosure: Leak Confidential Records from a RAG AssistantIn browserPro

Advanced · 75 minIndirect Prompt Injection: Exfiltrate Data from a RAG AssistantIn browserfree

Advanced · 80 minRetrieval Poisoning: Win Top-k Across a Whole Query Class and Steer the AnswerIn browserPro

Advanced · 70 minCross-Tenant Leakage: Break RAG Metadata Isolation and Exfiltrate Another Tenant's ContractIn browserPro

Advanced · 80 minInsecure Output Handling: SSRF, SQLi, and Command Execution Through an Agent's ToolsIn browserPro

Advanced · 85 minInsecure Output Handling: Zero-Click Exfiltration Through Rendered Model Output (EchoLeak)In browserPro

Advanced · 75 minExcessive Agency: Turn a Support Ticket into a Privileged Action (Confused Deputy)In browserPro

Advanced · 80 minMemory Poisoning: Plant a Note That Re-Fires in a Fresh Session (Persistence)In browserPro

Advanced · 95 minMCP Tool Poisoning: Hijack an Agent Through a Tool Description (and a Rug Pull)In browserPro

Advanced · 75 minTool Shadowing: Hijack an Agent's Tool Selection With a Name CollisionIn browserPro

Advanced · 85 minInter-Agent Injection: Propagate a Morris II Worm Across a Two-Agent GraphIn browserPro

Advanced · 90 minFuzz an LLM App with garak: Run, Read, and Triage True vs False PositivesIn browserPro

Intermediate · 35 minBuild NeMo Guardrails for an AI Agent: Jailbreak & Topical RailsIn browserPro

Advanced · 90 minDefense in Depth: Wire Four Control Points Around a RAG AssistantIn browserPro

Advanced · 85 minDefend a RAG Assistant: Build a Guardrail Layer and an Attack-Success-Rate CI GateIn browserPro

Advanced · 85 minDefend a RAG Assistant: Block Indirect-Injection Exfil (EchoLeak)In browserPro

Advanced · 80 minBuild a RAG Firewall: Reject Poisoned Ingestion and Enforce Tenant IsolationIn browserPro

Advanced · 80 minDefend: Secret Isolation for a RAG AssistantIn browserPro

Advanced · 90 minDefend Excessive Agency: Re-scope a Tool Agent to Least Privilege (AuthZ + Human Approval Gate)In browserPro

Advanced · 90 minDefend the Agent Supply Chain: Verify, Pin, and Capability-Gate Your Tool RegistryIn browserPro

Advanced · 90 minDefend: A Contextual Output Mediator for XSS, SSRF, SQLi, and RCEIn browserPro

Intermediate · 55 minPII Detection and Redaction: Checksums, LLM Entity Extraction, Reversible Placeholders and a Leak TestIn browserPro

Intermediate · 60 minPII-Safe Multi-Tenant Chatbot: Signed Sessions, Redaction Vaults, Scoped Memory and ErasureIn browserPro

Intermediate · 50 minMembership Inference: Audit a Model for Training-Data Leakage Before It ShipsIn browserPro

Intermediate · 55 minAdversarial Examples: Fool an Image Classifier, Then Harden ItIn browserPro

Advanced · 60 minModel Extraction: Audit Your Scoring API Against Cloning, Then Defend ItIn browserPro

graded projects

Finished a track? Build one on your own

A graded project gives you a brief and a rubric, then scores every criterion with evidence from your code.

See a graded project

All 163 labs

163 labs

more lab collections:NVIDIA NIM vs NeMo Prompt injection examples LLM security defenses Train an LLM from scratch CUDA and GPU performance LLM inference optimization

pro

Every lab with Pro

All 163 labs across every track, plus every practice test and course. $29.99 a month, cancel any time.

See Pro

Questions about the labs

What do I need to install?

Nothing. Each lab opens in your browser with the code, data, models and a terminal already set up. GPU labs run on a real NVIDIA GPU that starts when you open them.

Which labs are free?

Five labs are free: your first AI call, an agent tool loop written without a framework, a RAG pipeline, an agent tool-call gate and an indirect prompt injection attack. Pro opens every lab.

How does the checking work?

Every step has a check that runs your code against the goal and tells you what is still wrong, so you know it works before you move on.

How are labs different from graded projects?

A lab walks you through a build step by step. A graded project gives you a brief and a rubric, and you build it on your own.

Do the labs cover NVIDIA and Claude certification topics?

Many do. The agent, RAG, fine-tuning and infrastructure tracks practise topics from the NVIDIA NCP-AAI, NCP-GENL and NCA-AIIO exams and the Anthropic Claude architect exams.