Ready-made course · 2 days · Advanced
Agentic RAG Systems
A two-day advanced course combining retrieval with agentic reasoning and tool use: multi-step retrieval, query planning, structured sources and a production architecture for complex knowledge work.
Static RAG answers a question with a single retrieve-then-generate pass. That is often enough. It fails when the question requires planning, multiple searches, comparison across sources, or a mix of documents and APIs. Agentic RAG is the attempt to do that work without turning the system into an unsupervised research assistant with no budget.
This course starts from the limits of static RAG, then builds the pieces of an agentic retrieval system: query planning, multi-step retrieval, tool-driven search, document selection, iterative retrieval and memory. Structured knowledge sources and APIs are combined with unstructured corpora. Planning, evaluation, security, latency and cost are treated as first-class design constraints.
The practical work is a complex system, not a toy. You implement a path that can plan, retrieve, call tools, keep intermediate state and produce a grounded answer with traces.
You leave able to design agentic retrieval where it is justified, and to keep static RAG where it is not.
- Who it is for
- Experienced AI engineers, developers and architects who already understand RAG and tool calling and need to compose them.
- Before you start
- Experience implementing RAG and tool calling, or completion of the RAG and agents courses. You should be comfortable with production application structure.
You will be able to
- Diagnose when static RAG is the wrong architecture for a knowledge task.
- Design query planning and multi-step retrieval without unbounded loops.
- Combine unstructured retrieval with APIs and structured sources in one orchestration.
- Implement iterative retrieval, document selection and memory of intermediate findings.
- Evaluate agentic retrieval for completeness, groundedness, latency and cost.
- Apply security controls so retrieved content and tools cannot expand authority.
- Specify a production architecture with traces, budgets and fallback to simpler retrieval.
Modules
8 quarter-day modules. Each one can go into a custom course on its own.
RAG as an architecture
- The stages: ingest, index, retrieve, assemble, generate and cite.
- Where RAG fits, and where fine-tuning or plain search fits better.
- The failure modes of each stage.
- Choosing a vector store and a framework, or neither.
Hybrid search and reranking
- Keyword search and where vectors lose to it.
- Hybrid retrieval and score fusion.
- Rerankers, query rewriting and generated FAQs.
- Lab: improve recall on the questions vector search misses.
Agentic retrieval
- Where single-shot RAG stops working.
- Query planning, decomposition and iterative retrieval.
- Knowing when to stop searching.
- Lab: turn a fixed RAG pipeline into a retrieval agent.
Retrieval over mixed sources
- Documents, databases and APIs behind one question.
- Text-to-SQL, and the guardrails it needs.
- Routing questions to the right source.
- Combining results into one grounded answer.
Knowledge graphs and structured retrieval
- When relationships matter more than similarity.
- Extracting entities and relations with an LLM.
- GraphRAG and its costs.
- Lab: answer multi-hop questions over a small graph.
Designing tools for models
- Tool names, descriptions and schemas a model uses correctly.
- Validating arguments before any side effect.
- Errors the model can recover from.
- Lab: wrap an existing API as a set of tools.
Evaluating agents and multi-step systems
- Scoring the outcome against scoring the path taken.
- Tool-call accuracy, step counts and recovery from errors.
- Simulated users and environments.
- Lab: evaluate an agent on a task set and find its weakest step.
Running RAG in production
- Keeping the index fresh: incremental updates and deletions.
- Re-embedding and migrating without downtime.
- Monitoring retrieval quality and answer quality.
- Cost and latency at scale.
Practical work
You build a multi-step retrieval system against a corpus that cannot be handled by a single search. The system plans queries, retrieves iteratively, can call at least one non-vector tool, and produces a grounded answer with traces and a cost/latency budget.
You take away
- A working agentic RAG system
- Planning and retrieval patterns for multi-hop questions
- Evaluation cases that static RAG fails and the agentic path should pass
- A production architecture with budgets, traces and fallbacks
Combine it with
- Building AI Agents · 2 days
- RAG: From Fundamentals to Production · 2 days