Neural Mastery
ENGINEERING LAB · NEURAL MASTERY

Design a system.
Find out where it breaks.

Start with a real problem. Sketch how the pieces connect, choose an approach, and test what happens when the conditions change. Leave with a decision you can explain.

243 build exercises
8 ways to explore
3 interactive decision labs

GUIDED LAB / 15 MINUTES

Keep a support assistant useful during an outage.

System design

Your assistant answers questions using a product manual. Its search service sometimes goes offline. Can you keep answers fast without showing customers outdated advice?

1. Make a prediction

2. Choose your design

Follow the question
QuestionAssistantLive searchSaved manualNo saved copy
Live search supplies current information. A saved manual adds a fallback, with the risk of stale advice.

3. Inspect the outcome

Run the experiment to follow your question through the system.
This is a qualitative teaching simulation, not a performance benchmark.

4. Explain your decision

BUILD IT YOURSELF

Build an Agent

Explore the working parts of an agent, from reading a request to checking its actions. Each stage gives you a small system to build and inspect.

Open the first build →
Explore all 12 stages
  1. Parse a Tool Call From Model Output
  2. Validate Tool Arguments Against a Schema
  3. Dispatch Tool Calls Without Crashing the Agent
  4. The Agent Loop
  5. Recover From Malformed and Failing Tool Calls
  6. Guardrails: Loop Detection and Token Budgets
  7. Trim Context Without Orphaning Tool Results
  8. Parallel Tool Calls With IDs
  9. Long-Term Memory Recall
  10. Plan-and-Execute With Dependencies
  11. Evaluate Your Agent
  12. Capstone: A Production Agent Loop

SKILLS TO BUILD

What will you get better at?

01

Frame the problem

Turn a vague request into a clear goal, constraints, and a way to recognize success.

Write a short brief →
02

Design the system

Decide where information lives, how components connect, and how failures are contained.

Draw a system map →
03

Test an assumption

Change one thing, compare results, and check whether the evidence supports your prediction.

Keep an experiment log →
04

Make a decision

Explain which trade-off you chose, what could go wrong, and when you would revisit it.

Save a decision note →

Understanding code, data, and model behavior still matters. These labs connect that knowledge to the choices you make when building with AI.

TRY A DIFFERENT KIND OF PROBLEM

Interactive Engineering Labs

Compare a search architecture, investigate an unreliable assistant, or review a change before release. Each exercise asks you to explain your reasoning.

TYPE: DESIGN & DECIDEILLUSTRATIVE MODEL

These numbers are a simplified teaching model. Use them to explore trade-offs, then benchmark your own workload; they are not measured production results.

Scenario: Design a 10M-Document Production RAG System

Corpus: 10M Docs
Traffic: 50K queries/day
SLA Target: P95 < 800ms
Citations: Strict Source Spans
Updates: Hourly Ingestion
Budget: $8,000 / month

Live System Consequences

Quality Score99 / 100Faithfulness & Recall
P95 Latency532 ms✓ Within 800ms budget
Monthly Infra Cost$6,300✓ Within $8K budget
Data Freshness~70 minIngestion & cache TTL
System ComplexityHighMaintenance surface
ARCHITECTURAL TRADE-OFF ANALYSIS
What you optimized:

Maximum groundedness and context precision using dense reranking and semantic hierarchy.

What you sacrificed:

Operational simplicity: Multi-stage pipeline requires complex distributed monitoring.

Where it will fail first:

OOM memory crashes when 10M embeddings and graph connections exceed server RAM.

EXPLORE THE COLLECTION

Find your next lab

Browse by the skill you want to strengthen, the kind of problem you enjoy, or your experience.

Choose an activity:
AI-Native Engineer12 problemsIntermediate

Build an Agent

Write a tool-using agent from scratch, one piece per problem: parsing, dispatch, the loop, guardrails, memory, planning, evals.

  1. 01TYPE: ORCHESTRATEParse a Tool Call From Model Output
  2. 02TYPE: ORCHESTRATEValidate Tool Arguments Against a Schema
  3. 03TYPE: ORCHESTRATEDispatch Tool Calls Without Crashing the Agent
  4. 04TYPE: ORCHESTRATEThe Agent Loop
  5. 05TYPE: ORCHESTRATERecover From Malformed and Failing Tool Calls
  6. 06TYPE: ORCHESTRATEGuardrails: Loop Detection and Token Budgets
  7. 07TYPE: ORCHESTRATETrim Context Without Orphaning Tool Results
  8. 08TYPE: ORCHESTRATEParallel Tool Calls With IDs
  9. 09TYPE: ORCHESTRATELong-Term Memory Recall
  10. 10TYPE: ORCHESTRATEPlan-and-Execute With Dependencies
  11. 11TYPE: EVALUATEEvaluate Your Agent
  12. 12TYPE: ORCHESTRATECapstone: A Production Agent Loop
Open complete Build an Agent track (12 challenges) →
Senior Engineer12 problemsIntermediate

Specify, Verify, Debug

The work left when an agent writes the code: turn requests into tests, debug production failures, measure LLM output, and decide what ships.

  1. 01TYPE: SPECIFYTurn the Request Into Tests
  2. 02TYPE: DECIDEThe Code Is Right, the Rule Is Wrong
  3. 03TYPE: DEBUGRead the Logs Before the Code
  4. 04TYPE: DECIDERetries Refund Twice
  5. 05TYPE: DEBUGStale Answers After a Policy Change
  6. 06TYPE: EVALUATEMeasure Retrieval Before Tuning It
  7. 07TYPE: EVALUATEWrite a Check That Agrees With People
  8. 08TYPE: REVIEWA Judge You Can Trust
  9. 09TYPE: EVALUATEWill It Hold 50 Requests a Second?
  10. 10TYPE: SPECIFYA Document Tells the Bot to Refund
  11. 11TYPE: INCIDENTShip It or Roll It Back
  12. 12TYPE: INCIDENTCapstone: The Incident Review
Open complete Specify, Verify, Debug track (12 challenges) →
Foundation19 problemsBeginner

Python for AI

The everyday Python behind data and model code: dicts, nesting, text, caches and small parsers.

  1. 01TYPE: IMPLEMENTCount Item Frequencies
  2. 02TYPE: IMPLEMENTDeduplicate List Preserving Order
  3. 03TYPE: IMPLEMENTInvert a Dictionary
  4. 04TYPE: IMPLEMENTChunk a List into Batches
  5. 05TYPE: IMPLEMENTClean and Tokenize Text
  6. 06TYPE: IMPLEMENTFlatten an Arbitrarily Nested List
  7. 07TYPE: IMPLEMENTRun-Length String Compression
  8. 08TYPE: IMPLEMENTSafe Nested Dictionary Traversal
  9. 09TYPE: IMPLEMENTFlatten Nested Dictionary with Delimiters
  10. 10TYPE: IMPLEMENTMerge Overlapping Intervals
  11. 11TYPE: IMPLEMENTStreaming Sliding Window Mean
  12. 12TYPE: IMPLEMENTLRU Cache Operation Simulator
  13. 13TYPE: IMPLEMENTPrefix Tree (Trie) Simulator
  14. 14TYPE: IMPLEMENTToken Bucket Rate Limiter Simulator
  15. 15TYPE: IMPLEMENTLevenshtein Edit Distance Metric
  16. 16TYPE: IMPLEMENTTime-To-Live (TTL) Cache Simulator
  17. 17TYPE: IMPLEMENTPackage Build Order and Cycle Resolver
  18. 18TYPE: IMPLEMENTRecursive Pure-Python JSON Serializer
  19. 19TYPE: IMPLEMENTAbstract Syntax Tree (AST) Evaluator
Open complete Python for AI track (19 challenges) →
Foundation18 problemsBeginner

NumPy & Data Wrangling

Scaling, encoding, splitting and reshaping data the way training pipelines actually need it.

  1. 01TYPE: IMPLEMENTNumPy Vectorized Min-Max Feature Scaling
  2. 02TYPE: IMPLEMENTNumPy Vectorized Z-Score Standardization
  3. 03TYPE: IMPLEMENTNumPy Vectorized One-Hot Matrix Encoding
  4. 04TYPE: IMPLEMENTVectorized Softmax Normalization
  5. 05TYPE: IMPLEMENTNumPy Vectorized Confusion Matrix
  6. 06TYPE: IMPLEMENTPandas GroupBy Metric Aggregation
  7. 07TYPE: IMPLEMENTPandas Missing Value Imputation Pipeline
  8. 08TYPE: IMPLEMENTVectorized Numerically Stable Log-Sum-Exp
  9. 09TYPE: IMPLEMENTVectorized Euclidean Distance Matrix via Gram Matrix
  10. 10TYPE: IMPLEMENTStratified Train-Test Split Partition
  11. 11TYPE: IMPLEMENTStreaming Moving Variance (Welford)
  12. 12TYPE: IMPLEMENTVectorized Batch Collator with Sequence Padding
  13. 13TYPE: IMPLEMENTVectorized Multi-Head Attention Reshape and Transpose
  14. 14TYPE: IMPLEMENTTime-Window Event Stream Sessionization
  15. 15TYPE: IMPLEMENTUser Cohort Retention Matrix Engine
  16. 16TYPE: IMPLEMENTVectorized Layer Normalization with Learnable Affine
  17. 17TYPE: IMPLEMENTVectorized Causal Triangular Attention Masking
  18. 18TYPE: IMPLEMENTFlashAttention Online Softmax Block Accumulator
Open complete NumPy & Data Wrangling track (18 challenges) →
Foundation18 problemsBeginner

Math for ML

Vectors, matrices, probability and optimisation, each implemented by hand so the formulas stop being abstract.

  1. 01TYPE: IMPLEMENTDot Product From Scratch
  2. 02TYPE: IMPLEMENTMatrix Multiplication From Scratch
  3. 03TYPE: IMPLEMENTEuclidean and Manhattan Vector Norms
  4. 04TYPE: IMPLEMENTVector Projection and Rejection
  5. 05TYPE: IMPLEMENTMatrix Determinant for Low-Order Systems
  6. 06TYPE: IMPLEMENTSample Mean and Variance From Scratch
  7. 07TYPE: IMPLEMENTSample Covariance Matrix
  8. 08TYPE: IMPLEMENTBayes' Rule Categorical Posterior
  9. 09TYPE: IMPLEMENTShannon Entropy, Cross-Entropy, and KL Divergence
  10. 10TYPE: IMPLEMENTCentral Finite Difference Gradient Approximation
  11. 11TYPE: IMPLEMENTJacobian Matrix Evaluation
  12. 12TYPE: IMPLEMENTClassical Momentum Gradient Descent Step
  13. 13TYPE: IMPLEMENTNewton-Raphson Optimization Step
  14. 14TYPE: IMPLEMENTPower Iteration for Dominant Eigenpair
  15. 15TYPE: IMPLEMENTMatrix Inverse via Gauss-Jordan Elimination
  16. 16TYPE: IMPLEMENTGram-Schmidt Orthonormalization
  17. 17TYPE: IMPLEMENTNumerically Stable Softmax and Cross-Entropy
  18. 18TYPE: IMPLEMENTConjugate Gradient Method Single Iteration
Open complete Math for ML track (18 challenges) →
Builder21 problemsIntermediate

Classical ML from Scratch

Regression, trees, k-means, naive Bayes, SVMs and the metrics that tell you whether any of it worked.

  1. 01TYPE: IMPLEMENTPrecision, Recall & F1 From a Confusion Matrix
  2. 02TYPE: IMPLEMENTLinear Regression Gradient Descent Step
  3. 03TYPE: IMPLEMENTDecision Tree Gini Impurity
  4. 04TYPE: IMPLEMENTDecision Tree Information Gain via Entropy
  5. 05TYPE: IMPLEMENTLinear Regression via the Normal Equation
  6. 06TYPE: IMPLEMENTBatch Gradient Descent for Linear Regression
  7. 07TYPE: IMPLEMENTLogistic Regression: Forward Pass + Log Loss
  8. 08TYPE: IMPLEMENTK-Nearest Neighbors Classifier
  9. 09TYPE: IMPLEMENTGaussian Naive Bayes Classifier
  10. 10TYPE: IMPLEMENTK-Means Clustering: Single Lloyd Step
  11. 11TYPE: IMPLEMENTK-Means++ Min Squared Centroid Distances
  12. 12TYPE: IMPLEMENTK-Fold Cross-Validation Split Generation
  13. 13TYPE: IMPLEMENTSVM Hinge Loss & Margin
  14. 14TYPE: IMPLEMENTGradient Boosting Pseudo-Residuals
  15. 15TYPE: IMPLEMENTAdaBoost Sample Weight Re-weighting
  16. 16TYPE: IMPLEMENTMean Average Precision at K (MAP@K)
  17. 17TYPE: IMPLEMENTDecision Tree Best Binary Split
  18. 18TYPE: IMPLEMENTROC AUC From Scratch (Rank-Based)
  19. 19TYPE: IMPLEMENTSilhouette Score for Cluster Quality
  20. 20TYPE: IMPLEMENTPCA: Explained Variance Ratio via Eigendecomposition
  21. 21TYPE: IMPLEMENTCoordinate Descent for Lasso Regression
Open complete Classical ML from Scratch track (21 challenges) →
Builder24 problemsIntermediate

Neural Networks by Hand

Forward passes, backprop, optimisers, convolutions and recurrent cells, the pieces inside every framework.

  1. 01TYPE: IMPLEMENTDense Layer Forward Pass
  2. 02TYPE: IMPLEMENTReLU Backward Gradient Pass
  3. 03TYPE: IMPLEMENTNumerically Stable Softmax
  4. 04TYPE: IMPLEMENTCategorical Cross-Entropy Loss
  5. 05TYPE: IMPLEMENTMean Squared Error Loss Gradient
  6. 06TYPE: IMPLEMENTKaiming / He Initialization Variance
  7. 07TYPE: IMPLEMENTConv2D Output Spatial Dimension Calculator
  8. 08TYPE: IMPLEMENT2D Max Pooling Forward Pass
  9. 09TYPE: IMPLEMENTBounding Box Intersection over Union (IoU)
  10. 10TYPE: IMPLEMENTDense Layer Backward Pass
  11. 11TYPE: IMPLEMENTSoftmax Gradient (Vector-Jacobian Product)
  12. 12TYPE: IMPLEMENTSGD with Momentum Parameter Step
  13. 13TYPE: IMPLEMENTAdam Optimizer Step with Bias Correction
  14. 14TYPE: IMPLEMENTInverted Dropout Forward Pass
  15. 15TYPE: IMPLEMENT1D Batch Normalization Forward Pass
  16. 16TYPE: IMPLEMENTGlobal Gradient Norm Clipping
  17. 17TYPE: IMPLEMENT2D Convolution From Scratch
  18. 18TYPE: IMPLEMENTMulti-Channel 2D Convolution
  19. 19TYPE: IMPLEMENT2D Max Pooling Backward Pass Gradient Router
  20. 20TYPE: IMPLEMENTResNet Basic Residual Block Forward Pass
  21. 21TYPE: IMPLEMENTVanilla Elman RNN Step Forward
  22. 22TYPE: IMPLEMENTLSTM Cell Forward Pass
  23. 23TYPE: IMPLEMENTConv2D Backward Pass Gradient w.r.t. Kernel Weights
  24. 24TYPE: IMPLEMENTTwo-Layer MLP Training Step
Open complete Neural Networks by Hand track (24 challenges) →
Builder22 problemsIntermediate

Inside an LLM

Attention, masks, positional encodings, sampling, the KV cache and the tricks that make inference fast.

  1. 01TYPE: IMPLEMENTScaled Dot-Product Attention Score
  2. 02TYPE: IMPLEMENTConstruct Causal Attention Mask
  3. 03TYPE: IMPLEMENTTemperature Scaled Softmax
  4. 04TYPE: IMPLEMENTGreedy Decoding Step
  5. 05TYPE: IMPLEMENTTop-K Logit Filtering
  6. 06TYPE: IMPLEMENTTop-P (Nucleus) Filtering
  7. 07TYPE: IMPLEMENTCross-Entropy Loss from Logits
  8. 08TYPE: IMPLEMENTMulti-Head Attention: Split Heads
  9. 09TYPE: IMPLEMENTRMS Normalization From Scratch
  10. 10TYPE: IMPLEMENTSinusoidal Positional Encoding
  11. 11TYPE: IMPLEMENTRotary Positional Embedding (RoPE) From Scratch
  12. 12TYPE: IMPLEMENTPerplexity from Token Log-Probabilities
  13. 13TYPE: IMPLEMENTCalculate KV-Cache Memory Footprint
  14. 14TYPE: IMPLEMENTKV Cache Size With Grouped Query Attention
  15. 15TYPE: IMPLEMENTKV Cache State Manager
  16. 16TYPE: IMPLEMENTBeam Search Step with Pruning
  17. 17TYPE: IMPLEMENTMerge a LoRA Adapter Into the Base Weight
  18. 18TYPE: IMPLEMENTGreedy Longest-Match WordPiece Tokenization
  19. 19TYPE: IMPLEMENTSpeculative Decoding Rejection Sampler
  20. 20TYPE: IMPLEMENTPagedAttention Block Allocator
  21. 21TYPE: IMPLEMENTContinuous Batching Iteration Scheduler
  22. 22TYPE: IMPLEMENTMixture-of-Experts Top-K Routing
Open complete Inside an LLM track (22 challenges) →
Builder21 problemsIntermediate

RAG & Retrieval

Chunking, vector search, hybrid ranking, re-ranking and the checks that catch an ungrounded answer.

  1. 01TYPE: DESIGNFixed-Size Chunking With Overlap
  2. 02TYPE: DESIGNCosine Similarity Between Vectors
  3. 03TYPE: DESIGNSentence-Boundary-Aware Chunking
  4. 04TYPE: DESIGNBrute-Force K-Nearest-Neighbor Search
  5. 05TYPE: DESIGNBuild an Inverted Index
  6. 06TYPE: DESIGNReciprocal Rank Fusion
  7. 07TYPE: DESIGNDense + Sparse Score Fusion
  8. 08TYPE: DESIGNContext Window Token Budget Fitting
  9. 09TYPE: DESIGNRetrieval Recall@K
  10. 10TYPE: DESIGNScalar Quantize a Vector
  11. 11TYPE: DESIGNBinary Quantization and Hamming Distance
  12. 12TYPE: DESIGNMerge Top-K Results From Multiple Shards
  13. 13TYPE: DESIGNFiltered ANN Search With Metadata Predicate
  14. 14TYPE: DESIGNHNSW Greedy Search Single Hop
  15. 15TYPE: DESIGNGrounding Check via N-Gram Overlap
  16. 16TYPE: DESIGNFaithfulness Evaluation Score
  17. 17TYPE: DESIGNCorrective RAG: Grade Retrieved Document Relevance
  18. 18TYPE: DESIGNDecompose a Compound Question Into Subquestions
  19. 19TYPE: DESIGNBFS Shortest Path Between Two Entities
  20. 20TYPE: DESIGNMaximal Marginal Relevance (MMR) Selection Step
  21. 21TYPE: DESIGNOne PageRank Iteration Step
Open complete RAG & Retrieval track (21 challenges) →
Engineer24 problemsAdvanced

Agents in Production

What surrounds the loop: MCP plumbing, caching, fallbacks, security checks, graphs and observability.

  1. 01TYPE: IMPLEMENTCorrelate JSON-RPC Response to Pending Request
  2. 02TYPE: IMPLEMENTCursor-Based Pagination for an MCP Tool List
  3. 03TYPE: IMPLEMENTTruncate Oversized Tool Output
  4. 04TYPE: IMPLEMENTStreaming Stop Sequence Cutter
  5. 05TYPE: IMPLEMENTJSON-RPC 2.0 Request Shape Validation
  6. 06TYPE: IMPLEMENTParse Content-Length Stdio Framing
  7. 07TYPE: IMPLEMENTMCP Session Lifecycle State Transition
  8. 08TYPE: IMPLEMENTIdempotency-Aware Retry Safety Check
  9. 09TYPE: IMPLEMENTTool Description Budget Fitting for Context Window
  10. 10TYPE: IMPLEMENTProvider Fallback Cascade
  11. 11TYPE: IMPLEMENTExact Match Semantic Prompt Cache
  12. 12TYPE: IMPLEMENTCircuit Breaker State Transition
  13. 13TYPE: IMPLEMENTDetect Prompt Injection Markers in Tool Output
  14. 14TYPE: IMPLEMENTDetect Shell Metacharacters in Tool Arguments
  15. 15TYPE: IMPLEMENTRedact PII Patterns From Text
  16. 16TYPE: IMPLEMENTState Update Merge Reducer
  17. 17TYPE: IMPLEMENTFan-In Aggregation of Parallel Branch Results
  18. 18TYPE: IMPLEMENTSupervisor Worker Routing Decision
  19. 19TYPE: IMPLEMENTVerify Audit Log Hash Chain Integrity
  20. 20TYPE: EVALUATEAggregate Trace Spans Into a Tree
  21. 21TYPE: EVALUATEInter-Rater Agreement (Cohen's Kappa)
  22. 22TYPE: EVALUATECompute Eval Confidence Interval (Wilson Score)
  23. 23TYPE: IMPLEMENTDeadlock Detection via Wait-For Graph Cycle
  24. 24TYPE: IMPLEMENTDetect Cyclic Tool Call Chain
Open complete Agents in Production track (24 challenges) →
Senior Engineer14 problemsAdvanced

ML Systems & MLOps

Training schedules, drift, rollouts, experiments and the arithmetic of serving models.

  1. 01TYPE: DESIGNDeterministic Hash-Based Train/Test Split
  2. 02TYPE: DESIGNLinear Learning-Rate Warmup Schedule
  3. 03TYPE: DESIGNCosine Annealing Learning Rate
  4. 04TYPE: DESIGNEarly Stopping Patience Check
  5. 05TYPE: DESIGNTraining Batch GPU Memory Estimator
  6. 06TYPE: DESIGNPopulation Stability Index (PSI) for Drift Detection
  7. 07TYPE: DESIGNFeature Skew Detection Between Training and Serving
  8. 08TYPE: DESIGNCanary Rollout Traffic Assignment
  9. 09TYPE: DESIGNINT8 Weight Quantization From Scratch
  10. 10TYPE: DESIGNParallel Sum Reduction (WebGPU)
  11. 11TYPE: DESIGNConsistent Hash Ring Lookup
  12. 12TYPE: DESIGNA/B Test Statistical Significance (Two-Proportion Z-Test)
  13. 13TYPE: DESIGNPage-Hinkley Concept Drift Statistic Update
  14. 14TYPE: DESIGNPipeline DAG Topological Sort
Open complete ML Systems & MLOps track (14 challenges) →
Builder38 problemsIntermediate

Coding Interview Patterns

The classic patterns interviews still test: hashing, two pointers, windows, stacks, trees, graphs and DP.

  1. 01TYPE: IMPLEMENTTwo Sum
  2. 02TYPE: IMPLEMENTValid Anagram
  3. 03TYPE: IMPLEMENTValid Palindrome
  4. 04TYPE: IMPLEMENTValid Parentheses
  5. 05TYPE: IMPLEMENTReverse a Singly Linked List
  6. 06TYPE: IMPLEMENTLinked List Cycle Detection
  7. 07TYPE: IMPLEMENTBinary Search
  8. 08TYPE: IMPLEMENTMaximum Depth of Binary Tree
  9. 09TYPE: IMPLEMENTFind if Path Exists in Graph
  10. 10TYPE: IMPLEMENTHouse Robber
  11. 11TYPE: IMPLEMENTGroup Anagrams
  12. 12TYPE: IMPLEMENTTop K Frequent Elements
  13. 13TYPE: IMPLEMENTProduct of Array Except Self
  14. 14TYPE: IMPLEMENTLongest Consecutive Sequence
  15. 15TYPE: IMPLEMENT3Sum
  16. 16TYPE: IMPLEMENTContainer With Most Water
  17. 17TYPE: IMPLEMENTLongest Substring Without Repeating Characters
  18. 18TYPE: IMPLEMENTSubarray Sum Equals K
  19. 19TYPE: IMPLEMENTEvaluate Reverse Polish Notation
  20. 20TYPE: IMPLEMENTSearch in Rotated Sorted Array
  21. 21TYPE: IMPLEMENTFind First and Last Position of Element in Sorted Array
  22. 22TYPE: IMPLEMENTDiameter of Binary Tree
  23. 23TYPE: IMPLEMENTBinary Tree Zigzag Level Order Traversal
  24. 24TYPE: IMPLEMENTLowest Common Ancestor of a Binary Tree
  25. 25TYPE: IMPLEMENTNumber of Islands in 2D Grid
  26. 26TYPE: IMPLEMENTCourse Schedule: Cycle Detection in Directed Graph
  27. 27TYPE: IMPLEMENTCourse Schedule II: Topological Order Recovery
  28. 28TYPE: IMPLEMENTDijkstra's Single-Source Shortest Paths
  29. 29TYPE: IMPLEMENTLongest Common Subsequence
  30. 30TYPE: IMPLEMENTPartition Equal Subset Sum
  31. 31TYPE: IMPLEMENTDecode Ways
  32. 32TYPE: IMPLEMENTNon-overlapping Intervals
  33. 33TYPE: IMPLEMENTTrapping Rain Water
  34. 34TYPE: IMPLEMENTMinimum Window Substring
  35. 35TYPE: IMPLEMENTSliding Window Maximum
  36. 36TYPE: IMPLEMENTLargest Rectangle in Histogram (Monotonic Stack)
  37. 37TYPE: IMPLEMENTBinary Tree Maximum Path Sum
  38. 38TYPE: IMPLEMENTMedian of Two Sorted Arrays
Open complete Coding Interview Patterns track (38 challenges) →