Algo
Path
Curriculum
Pricing
Sign in
Get access
Curriculum
/
Agentic AI
RLHF and preference tuning
16 min read
This lesson is locked
Get full access to all 25 modules and 272 lessons.
Unlock — from $7/month
Sign in
The ReAct loop
Planning agents
Multi-agent systems
Memory architecture
Human-in-the-loop design
Embeddings and vector search
Chunking strategies
RAG pipeline anatomy
Hybrid search and reranking
Evaluating RAG
Structured output
Chain of thought and variants
Prompt injection and adversarial inputs
Context management in long sessions
When to fine-tune vs. prompt
LoRA and parameter-efficient fine-tuning
RLHF and preference tuning
Evaluation and preventing regression
Latency and cost tradeoffs
Observability for agents
Safety and guardrails
Agent state management
Deployment patterns
LoRA and parameter-efficient fine-tuning
Evaluation and preventing regression