Challenges
148 challenges available
All🎯 Prompt Engineering🤖 Agentic Architectures🔍 RAG & Retrieval🛡️ AI Security📊 Evaluation & Benchmarks🔧 Fine-Tuning & Training⚙️ LLM Infrastructure👁️ Multimodal & Vision📖 Know Your Model
⚙️ LLM Infrastructure
Token Pricing
Very Easy
0 solves50 pts
🔍 RAG & Retrieval
Chunking 101 [LangChain]
Very Easy
0 solves50 pts
📊 Evaluation & Benchmarks
Vibe Check Problem
Very Easy
0 solves50 pts
⚙️ LLM Infrastructure
Streaming Responses
Very Easy
0 solves50 pts
👁️ Multimodal & Vision
Vision-Language Models
Very Easy
0 solves50 pts
📊 Evaluation & Benchmarks
Vibe Check vs Systematic Eval
Very Easy
0 solves50 pts
⚙️ LLM Infrastructure
Streaming
Very Easy
0 solves50 pts
🎯 Prompt Engineering
The System Prompt
Very Easy
0 solves50 pts
🎯 Prompt Engineering
Token Limits
Very Easy
0 solves50 pts
⚙️ LLM Infrastructure
Token Economics
Very Easy
0 solves50 pts
🤖 Agentic Architectures
Function Calling
Very Easy
0 solves50 pts
📖 Know Your Model
The RTFM Challenge
Very Easy
0 solves50 pts
🎯 Prompt Engineering
Temperature & Creativity
Very Easy
1 solve50 pts
📊 Evaluation & Benchmarks
BLEU Limitation
Easy
0 solves100 pts
🔧 Fine-Tuning & Training
Epochs and Overfitting
Easy
0 solves100 pts
📖 Know Your Model
Model Cards
Easy
0 solves100 pts
⚙️ LLM Infrastructure
Quantization Basics
Easy
0 solves100 pts
🔧 Fine-Tuning & Training
LoRA
Easy
0 solves100 pts
👁️ Multimodal & Vision
OCR vs VLM
Easy
0 solves100 pts
⚙️ LLM Infrastructure
Embedding Models
Easy
0 solves100 pts
⚙️ LLM Infrastructure
Context Window vs Generation
Easy
0 solves100 pts
🎯 Prompt Engineering
Chain of Thought
Easy
0 solves100 pts
📖 Know Your Model
XML vs Markdown
Easy
0 solves100 pts
🛡️ AI Security
Injection 101
Easy
0 solves100 pts
🤖 Agentic Architectures
The ReAct Pattern
Easy
0 solves100 pts
🤖 Agentic Architectures
Human-in-the-Loop
Easy
0 solves100 pts
⚙️ LLM Infrastructure
Rate Limiting
Easy
0 solves100 pts
🎯 Prompt Engineering
Anthropic's Prompt Format
Easy
0 solves100 pts
🎯 Prompt Engineering
XML Tags in Prompts
Easy
0 solves100 pts
🛡️ AI Security
Jailbreak Categories
Easy
0 solves100 pts
🎯 Prompt Engineering
The RCTF Framework
Easy
0 solves100 pts
🎯 Prompt Engineering
XML Delimiters [Anthropic]
Easy
0 solves100 pts
🎯 Prompt Engineering
Anthropic Turn Format [Anthropic]
Easy
0 solves100 pts
📖 Know Your Model
Thinking Tokens
Easy
0 solves100 pts
📖 Know Your Model
Context Window Sizes
Easy
0 solves100 pts
🔧 Fine-Tuning & Training
Overfitting
Easy
0 solves100 pts
🎯 Prompt Engineering
The Perfect Prompt
Easy
0 solves100 pts
🤖 Agentic Architectures
Agent Memory Types
Easy
0 solves100 pts
🤖 Agentic Architectures
MCP Protocol [Anthropic]
Easy
0 solves100 pts
🤖 Agentic Architectures
Agent Memory
Easy
0 solves100 pts
🎯 Prompt Engineering
Self-Consistency
Easy
0 solves100 pts
🎯 Prompt Engineering
Structured Output [OpenAI]
Easy
0 solves100 pts
🛡️ AI Security
Jailbreak Patterns
Easy
0 solves100 pts
📊 Evaluation & Benchmarks
LLM-as-a-Judge Biases
Easy
0 solves100 pts
📊 Evaluation & Benchmarks
BLEU Score Limitations
Easy
0 solves100 pts
🛡️ AI Security
Prompt Leaking
Easy
0 solves100 pts
🛡️ AI Security
Output Filtering
Easy
0 solves100 pts
🔧 Fine-Tuning & Training
Instruction Tuning
Easy
0 solves100 pts
🔧 Fine-Tuning & Training
Data Quality
Easy
0 solves100 pts
🔍 RAG & Retrieval
Chunk Overlap
Easy
0 solves100 pts
⚙️ LLM Infrastructure
Quantization
Easy
0 solves100 pts
⚙️ LLM Infrastructure
Embeddings
Easy
0 solves100 pts
🔍 RAG & Retrieval
Lost in the Middle
Easy
0 solves100 pts
⚙️ LLM Infrastructure
Prefill vs Decode
Easy
0 solves100 pts
📊 Evaluation & Benchmarks
LLM-as-a-Judge
Easy
0 solves100 pts
🤖 Agentic Architectures
Tool Poisoning
Medium
0 solves150 pts
📖 Know Your Model
Prefill Technique
Medium
0 solves150 pts
🤖 Agentic Architectures
RAG vs RAG Agent
Medium
0 solves150 pts
🔧 Fine-Tuning & Training
Catastrophic Forgetting
Medium
0 solves150 pts
🛡️ AI Security
OWASP LLM #1
Medium
0 solves150 pts
🛡️ AI Security
PII Extraction
Medium
0 solves150 pts
🛡️ AI Security
Guardrails Pipeline
Medium
0 solves150 pts
🛡️ AI Security
Content Safety Classifier
Medium
0 solves150 pts
📊 Evaluation & Benchmarks
Faithfulness Score [RAGAS]
Medium
0 solves150 pts
🎯 Prompt Engineering
Constitutional AI Loop [Anthropic]
Medium
0 solves150 pts
🤖 Agentic Architectures
Loops vs Chains [LangChain]
Medium
0 solves150 pts
📊 Evaluation & Benchmarks
Elo Rating System [LMSYS]
Medium
0 solves150 pts
🔧 Fine-Tuning & Training
RLHF Pipeline
Medium
0 solves150 pts
🎯 Prompt Engineering
Retrieval-Augmented Prompting
Medium
0 solves150 pts
🤖 Agentic Architectures
Multi-Agent Orchestration
Medium
0 solves150 pts
⚙️ LLM Infrastructure
Continuous Batching
Medium
0 solves150 pts
👁️ Multimodal & Vision
CLIP Training
Medium
0 solves150 pts
📖 Know Your Model
System Prompt Behavior
Medium
0 solves150 pts
📖 Know Your Model
Tool Use Formats
Medium
0 solves150 pts
🎯 Prompt Engineering
Prompt Caching [Anthropic]
Medium
0 solves150 pts
🎯 Prompt Engineering
Few-Shot Mastery
Medium
0 solves150 pts
🎯 Prompt Engineering
The Meta-Prompt
Medium
0 solves150 pts
🤖 Agentic Architectures
Retrieval-Augmented Agents
Medium
0 solves150 pts
🤖 Agentic Architectures
Tool Use Poisoning
Medium
0 solves150 pts
📖 Know Your Model
Llama Prompt Format
Medium
0 solves150 pts
🔍 RAG & Retrieval
Parent Document Retrieval
Medium
0 solves150 pts
🔍 RAG & Retrieval
Re-Ranking
Medium
0 solves150 pts
🔍 RAG & Retrieval
Query Expansion
Medium
0 solves150 pts
🔍 RAG & Retrieval
Embedding Collapse
Medium
0 solves150 pts
🤖 Agentic Architectures
Parallel Tool Calls
Medium
0 solves150 pts
📖 Know Your Model
Prompt Caching Providers
Medium
0 solves150 pts
🛡️ AI Security
OWASP LLM Top 10
Medium
0 solves150 pts
🛡️ AI Security
PII Leakage
Medium
0 solves150 pts
🛡️ AI Security
Guardrails Architecture
Medium
0 solves150 pts
📊 Evaluation & Benchmarks
Benchmark Contamination
Medium
0 solves150 pts
🛡️ AI Security
Content Safety Classifiers
Medium
0 solves150 pts
📊 Evaluation & Benchmarks
Elo Ratings
Medium
0 solves150 pts
🔍 RAG & Retrieval
Hybrid Search
Medium
0 solves150 pts
🔧 Fine-Tuning & Training
Synthetic Data
Medium
0 solves150 pts
🔧 Fine-Tuning & Training
RLHF
Medium
0 solves150 pts
🛡️ AI Security
Indirect Prompt Injection
Medium
0 solves150 pts
🛡️ AI Security
Indirect Injection
Medium
0 solves150 pts
🔧 Fine-Tuning & Training
PEFT
Medium
0 solves150 pts
🔧 Fine-Tuning & Training
QLoRA
Medium
0 solves150 pts
📊 Evaluation & Benchmarks
Hallucination Detection
Medium
0 solves150 pts
⚙️ LLM Infrastructure
KV Cache
Medium
0 solves150 pts
🎯 Prompt Engineering
Constitutional AI Prompting
Medium
0 solves150 pts
👁️ Multimodal & Vision
Image Tokenization
Medium
0 solves150 pts
👁️ Multimodal & Vision
Document Understanding
Medium
0 solves150 pts
👁️ Multimodal & Vision
Visual Prompting
Medium
0 solves150 pts
👁️ Multimodal & Vision
CLIP Embeddings
Medium
0 solves150 pts
🎯 Prompt Engineering
Negative Prompting
Medium
0 solves150 pts
⚙️ LLM Infrastructure
Batching Strategies
Medium
0 solves150 pts
📊 Evaluation & Benchmarks
Answer Relevance [RAGAS]
Medium
0 solves150 pts
🎯 Prompt Engineering
Few-Shot Balance
Medium
0 solves150 pts
🎯 Prompt Engineering
Meta-Prompting
Medium
0 solves150 pts
🎯 Prompt Engineering
Context Ordering
Medium
0 solves150 pts
🤖 Agentic Architectures
Supervisor Pattern
Medium
0 solves150 pts
🔧 Fine-Tuning & Training
Training Data Poisoning
Hard
0 solves200 pts
🤖 Agentic Architectures
The Context Window Problem
Hard
0 solves200 pts
🛡️ AI Security
Sandwich Defense
Hard
0 solves200 pts
🎯 Prompt Engineering
Tree of Thoughts
Hard
0 solves200 pts
🎯 Prompt Engineering
Prompt Decomposition
Hard
0 solves200 pts
🎯 Prompt Engineering
System Prompt Extraction
Hard
0 solves200 pts
🎯 Prompt Engineering
Prompt Injection via Markdown
Hard
0 solves200 pts
🤖 Agentic Architectures
Agent Evaluation
Hard
0 solves200 pts
🤖 Agentic Architectures
Reflection Pattern
Hard
0 solves200 pts
🤖 Agentic Architectures
Planning Agents
Hard
0 solves200 pts
🔍 RAG & Retrieval
HyDE
Hard
0 solves200 pts
🔍 RAG & Retrieval
Contextual Compression
Hard
0 solves200 pts
🔍 RAG & Retrieval
Context Relevance Score [RAGAS]
Hard
0 solves200 pts
🛡️ AI Security
Red Teaming
Hard
0 solves200 pts
📊 Evaluation & Benchmarks
G-Eval
Hard
0 solves200 pts
🛡️ AI Security
Token Smuggling
Hard
0 solves200 pts
📊 Evaluation & Benchmarks
Regression Testing for LLMs
Hard
0 solves200 pts
🔧 Fine-Tuning & Training
DPO vs RLHF
Hard
0 solves200 pts
🔧 Fine-Tuning & Training
Model Merging
Hard
0 solves200 pts
🔧 Fine-Tuning & Training
Training Data Poisoning
Hard
0 solves200 pts
📊 Evaluation & Benchmarks
Human Preference Prediction
Hard
0 solves200 pts
⚙️ LLM Infrastructure
Model Distillation
Hard
0 solves200 pts
👁️ Multimodal & Vision
Multimodal RAG
Hard
0 solves200 pts
👁️ Multimodal & Vision
Vision Hallucinations
Hard
0 solves200 pts
⚙️ LLM Infrastructure
Speculative Decoding
Hard
0 solves200 pts
🎯 Prompt Engineering
Markdown Exfiltration
Hard
0 solves200 pts
🤖 Agentic Architectures
Context Window Saturation
Hard
0 solves200 pts
📊 Evaluation & Benchmarks
LLM Regression Testing
Hard
0 solves200 pts
🔧 Fine-Tuning & Training
DPO
Hard
0 solves200 pts
⚙️ LLM Infrastructure
Distillation
Hard
0 solves200 pts
🤖 Agentic Architectures
Computer Use [Anthropic]
Expert
0 solves300 pts
🔍 RAG & Retrieval
Knowledge Graph RAG
Expert
0 solves300 pts
🛡️ AI Security
Confused Deputy
Expert
0 solves300 pts
🤖 Agentic Architectures
Computer Use Agents
Expert
0 solves300 pts
🎯 Prompt Engineering
Dual LLM Pattern
Expert
0 solves300 pts