Agentic AI in Practice: Build Proactive LLM Agents with LangChain, RAG & Vector Search
Sub Category
- No-Code Development
{inAds}
Objectives
- Distinguish LLM chat apps from agentic systems across autonomy, tools, and memory
- Apply the Perceive → Reason → Act loop to multi-step, goal-directed tasks
- Orchestrate Model–Controller–Prompter (MCP) style workflows for agents
- Implement Retrieval-Augmented Generation (RAG) with grounding and citations
- Integrate web search (Tavily) and LLM ranking to fetch and summarize sources
- Persist interaction history using SQLite and migrate embeddings to ChromaDB
- Engineer topic “pillars,” weights, and recency decay to personalize results
- Perform semantic re-ranking to improve recommendation quality and diversity
- Mitigate agent risks including prompt injection, memory poisoning, and spoofing
- Evaluate agent performance with offline tests and scenario-based checks
- Package and ship a CLI news-curation agent with reproducible configs and prompts
Pre Requisites
- Working knowledge of Python and virtual environments; comfort with CLI & Git.
- Understanding of HTTP APIs and JSON; basic familiarity with LLM prompts.
FAQ
- Q. How long do I have access to the course materials?
- A. You can view and review the lecture materials indefinitely, like an on-demand channel.
- Q. Can I take my courses with me wherever I go?
- A. Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
{inAds}
Coupon Code(s)