← 🤖 Retrieval & AgentsNEXT IN RETRIEVAL & AGENTSAgent Evaluation and Trajectory Analysis→
Core
Agentic and Corrective RAG
Standard RAG retrieves once and generates; agentic RAG wraps retrieval in a loop so the model decides whether to retrieve, what to query, evaluates the results, and retrieves again until it has what it needs. Corrective RAG adds a grader that checks retrieval quality and takes corrective action (re-retrieve, web search, or discard) when the context is poor. Applied-AI interviews probe it because complex, multi-hop questions defeat single-shot RAG, and self-correcting retrieval is the fix, at the cost of more calls and agent-reliability concerns.
a free account unlocks the core curriculum tier · no card
TAUGHT IN THESE COURSES
This concept is a reference. These lessons put it in sequence, with what comes before and after it.
Applied AI Engineering·Tools and your first agentSign in12mTry these five things before you build an agentNow that you can build an agent, here is the ladder of cheaper designs to exhaust first. Each rung handles a large share of what people reach loops for, and moving up one rung at a time is how you end with a system you can operate.Agent Engineering·Memory and contextSign in14mState that has to survive the processOnce a run can pause for approval, be retried, or outlive a deployment, its progress has to live somewhere durable. This lesson covers what to checkpoint, why steps must be safe to repeat, and how retrieval changes when an agent is the one searching.
RELATED CONCEPTS
PRACTICE THIS IN REAL QUESTIONS
RAG & Agent System DesignWhat is agentic RAG, and how does it differ from standard (single-shot) RAG?→System Design for AI in ProductionDesign a deep research agent that answers complex questions by searching and synthesizing many sources.→RAG & Agent System DesignWhat is Self-RAG / adaptive retrieval, and how does the model decide when to retrieve?→System Design for AI in ProductionDesign a multi-agent customer support system with escalation to humans.→System Design for AI in ProductionDesign an AI code review system that comments on pull requests.→RAG & Agent System DesignWhat is the Plan-and-Execute agent pattern, and how does it compare to ReAct?→
COMPANIES THAT ASSUME THIS