RAG Systems & Agentic Workflows with Pinecone and LangGraph | Board Infinity
Home/Courses/AI Agents/RAG Systems & Agentic Workflows
Intermediate Course 2 of 3 · AI Agents

Build RAG systems that retrieve, reason and respond.

Give LLMs access to the right knowledge, then turn retrieval into intelligent workflows. RAG Systems & Agentic Workflows with Pinecone and LangGraph takes you from embeddings and vector search to stateful agents you can trace and debug.

Enroll on Coursera
2 weeks at 10 hrs/week 4 modules · 14 assignments Intermediate level English · 9 languages available
Want a coach alongside the course? See 1:1 coaching
Board Infinity287 courses · 479,274 learners on Coursera
Loading video… Introduction to the course · 9:46

Learn by building

Pipelines, vector indexes and agents, built in labs

Certificate included

Shareable on LinkedIn the day you finish

Part of a 3-course path

Course 2 of the AI Agents specialization

6 Lakh+learners on our Coursera courses
10+domains covered
270+courses
57+specializations
01 About the course

From a question, to the right context, to an agent that acts on it.

Four modules that take you from retrieval basics to production-ready agent pipelines.

4
Modules
Retrieval to observability
26
Video lessons
Including hands-on labs
14
Assignments
Practice and graded quizzes
2 wks
At 10 hours a week
Self-paced, flexible deadlines

RAG Systems & Agentic Workflows equips you to build intelligent AI systems that retrieve, reason and respond using real-world data, with tools like ChromaDB, Pinecone, LangChain, LangFuse and Python.

You start with Retrieval-Augmented Generation - connecting language models to external knowledge with embeddings and similarity search. Then come vector databases and semantic search across Chroma, Pinecone and FAISS, and conversational agents with LangGraph, session memory and retrieval-driven Q&A.

The final module is about optimization, debugging and observability: tracing agent runs, visualizing latency, and improving outputs with query transformation and reranking.

Inside the course
01Fundamentals of Retrieval-Augmented Generation≈ 4h 02Vector Databases and Semantic Search≈ 5h 03Conversational Agents and Workflows≈ 6h 04Optimization, Debugging, and Observability≈ 4h
02 Who it's for

For builders ready to move beyond simple prompting.

An intermediate course - you should be comfortable writing Python before you start.

AI developers

AI developers

Building LLM applications that need access to external knowledge.

GenAI

GenAI practitioners

Moving from basic LLM applications toward retrieval and agentic workflows.

Python

Python developers

Comfortable with Python and ready to build practical RAG and agent systems.

AI engineering

AI engineers

Working on vector search, orchestration, memory, observability and optimization.

03 What you'll learn

Four capabilities, in the order they build.

These are the four learning outcomes Coursera lists for the course - one for each module.

Module 1

Build end-to-end RAG pipelines

Connect LLMs with external knowledge sources using embeddings and vector search.

Module 2

Design and query vector databases

Use ChromaDB, Pinecone and FAISS for context-aware semantic retrieval.

Module 3

Create conversational agents

Multi-step agents with session memory, state management and retrieval-driven Q&A.

Module 4

Optimize and debug agent workflows

Use observability tools like LangFuse, W&B and OpenTelemetry to improve agents.

1:1 coaching · optional add-on

Build with 1:1 coaching from industry experts.

A dedicated coach who builds AI systems for a living - someone who can tell you why retrieval is returning the wrong chunks, and whether your agent is ready for real users.

Book a demo session
  • A coach matched to your goal in 24 hours
  • A written roadmap you keep
  • Weekly sessions for as long as you want them

60-minute demo session · 100% refundable · no obligation to continue

Debug your retrieval

Chunking, embeddings and reranking choices, checked against your data.

Review your agent

Graph design, memory and tool use reviewed by someone who ships agents.

Get it production-ready

Tracing, evaluation and latency, done the way teams run it in production.

Aim it at a role

Which AI engineering roles this opens, and what to build next.

2,000+Industry coaches
16Domains covered
4.8/5Average coach rating
48,000+Sessions delivered
04 Syllabus

Four modules, from retrieval to agents.

Coursera lists this course at 2 weeks of study at 10 hours a week, fully self-paced. Every module lists its learning objectives, its content, and what you'll walk out with.

26 videos 10 readings 14 assignments 2 weeks at 10 hrs/week
Learning objectives - by the end of this module you can:
  • Explain the concept and workflow of RAG systems
  • Break down the RAG architecture, from query to grounded answer
  • Use embeddings and similarity search to retrieve relevant context
  • Build a simple RAG pipeline, evaluate its responses and avoid common pitfalls
What's inside
6 videos63 min
2 readings60 min
3 assignments + 1 plugin125 min
Topics covered
Introduction to RAG RAG architecture Embeddings in action Similarity search Building a simple RAG pipeline Evaluating RAG responses
You'll build: a working RAG pipeline that grounds an LLM's answers in your own data.
Learning objectives - by the end of this module you can:
  • Build vector indexes using Chroma or Pinecone
  • Compare FAISS, Chroma and Pinecone and their performance tradeoffs
  • Optimize queries and combine vector and keyword search
  • Ingest and chunk data, and index a product knowledge base in a lab
What's inside
7 videos83 min
3 readings90 min
4 assignments150 min
Topics covered
Vector databases 101 FAISS & Chroma Pinecone for scalable RAG Query optimization Hybrid search Data ingestion & chunking
You'll build: a searchable vector index of a product knowledge base, in a hands-on lab.
Learning objectives - by the end of this module you can:
  • Design state-based conversational workflows
  • Explain agentic workflows and compare agent architectures
  • Build workflows and agent architectures with LangGraph
  • Add long-term memory and build retrieval-aware multi-step agents
What's inside
7 videos99 min
3 readings90 min
4 assignments150 min
Topics covered
Agentic workflows Agent architectures LangGraph workflow design Context & memory Long-term memory agents Building a Q&A chatbot
You'll build: a stateful, memory-aware Q&A agent that retrieves before it answers.
Learning objectives - by the end of this module you can:
  • Diagnose agent performance issues using observability tools
  • Set up tracing with LangSmith, or LangFuse as an alternative
  • Improve outputs with query transformation and reranking
  • Optimize a full pipeline, worked through as a case study
What's inside
6 videos81 min
2 readings60 min
3 assignments120 min
Topics covered
Why observability matters LangSmith setup & tracing LangFuse Query transformation Reranking Pipeline optimization
You'll leave with: traced, measurable agent pipelines - and a method for making them faster and more accurate.
05 Tools & skills

The stack behind production RAG and agents.

The tools you build with across the four modules, and the skills you leave with.

Vector databases

Pinecone, Chroma & FAISS

Vector indexes, semantic and hybrid search, and chunking - Module 2.

Orchestration

LangChain & LangGraph

Pipelines, state-based workflows and agent architectures with memory - Module 3.

Observability

LangSmith & LangFuse

Tracing, monitoring and debugging agent runs, with OpenTelemetry - Module 4.

Language

Python

The code behind every pipeline, embedding call and agent in the course.

Skills you leave with

Twelve skills from the course, grouped the way RAG work actually splits - getting the right context, acting on it, and running it reliably.

Retrieval

Finding the right context for every question.

  • Retrieval-augmented generation
  • Embeddings
  • Vector databases
  • Large language modeling

Agents

Turning retrieval into multi-step reasoning.

  • Generative AI agents
  • Agentic systems
  • Agentic workflows
  • Memory management

Production

The difference between a demo and a system people use.

  • Debugging
  • Performance tuning
  • AI workflows
  • LangChain
Certificate

Proof you can link to.

Finish the graded work and Board Infinity issues a shareable certificate through Coursera - add it to your LinkedIn profile, resume or CV.

Issued on completion of the graded quizzes in all four modules. It also counts toward the AI Agents: From Foundations to Applications specialization certificate.

On your profile in one click

Filed under Licenses & Certifications, where recruiters actually look.

Share it anywhere

On social media and in your next performance review.

Earned, not attended

Awarded on 14 practice and graded assignments - it certifies what you can build.

Two names on it

Board Infinity as the provider, Coursera as the platform.

06 Career impact

Every AI team is asking the same thing: who can make the model know our data?

These are the roles that rely on exactly this skill set.

Where these skills are in demand

AI Engineer

The role this course maps to most directly: building retrieval and agent systems.

GenAI Developer

LLM features grounded in company data, not just clever prompts.

LLM Application Developer

Chatbots and assistants with memory, state and retrieval-driven Q&A.

Machine Learning Engineer

Embeddings, vector search and evaluation alongside traditional ML work.

AI Solutions Architect

Choosing vector databases, orchestration and observability for a whole system.

Search & Retrieval Engineer

Semantic and hybrid search, chunking and reranking at scale.

MLOps / LLMOps Engineer

Tracing, monitoring and optimizing LLM pipelines in production.

Backend Developer

Adding retrieval and agent capabilities to existing products and APIs.

The honest comparison

What you're actually paying for

Every topic in this course exists free somewhere on the internet. Nobody is pretending otherwise. What a course adds is the order you learn it in, the practice that makes it stick, and something to show at the end.

What you get
This course
DIY with free content
A deliberate orderRAG → vectors → agents → observability
Four modules, each building on the last
Framework tutorials that never join up
Tools comparedNot just one vendor
FAISS, Chroma and Pinecone side by side
Whatever the blog post used
Practice with feedbackLearning that sticks
14 practice and graded quizzes
Nobody checks your work
Production thinkingBeyond the notebook
Tracing, reranking and optimization
Demos that stop at "it works"
Proof for recruitersShareable, on LinkedIn
Shareable Coursera certificate
Nothing to show
07 Where to go next

More from the AI Agents specialization.

This course stands on its own - but it's also the second step of a three-course path. Enrolling automatically enrolls you in the specialization.

Course 1

Agent Foundations and Prompt Engineering

LLM-based agent architectures and prompt patterns - the foundation of the path.

≈ 2 weeks
View course
You're here Course 2

RAG Systems & Agentic Workflows with Pinecone and LangGraph

Retrieval, vector databases, stateful agents and observability.

≈ 2 weeks · 4 modules
Back to top
Course 3

Advance Multi-Agent Systems & Production AI with LangSmith

Multi-agent orchestration and production AI, traced and evaluated with LangSmith.

≈ 2 weeks
View course
Related RAG and agent courses from Board Infinity
Go deeper on RAG

RAG from Scratch: Build a Knowledge-Powered Chatbot

Document ingestion, chunking and grounding, built into a deployable chatbot.

View course System design

AI Systems Design: RAG Pipelines and LLM Architecture

End-to-end RAG with LangChain and ChromaDB, plus chunking and retrieval strategy.

View course Build an agent

Building AI Research Agents: LangChain, RAG, and LangGraph

A complete research agent with tool use, web search and custom APIs.

View course

Board Infinity runs 270+ courses and 57 specializations on Coursera - browse the full catalogue.

Know exactly what you're signing up for.

4 modules · 26 lessons · 14 assignments · free PDF

08 FAQ

Common questions

Everything learners ask before enrolling, answered plainly.

About the course

Building intelligent AI systems that retrieve, reason and respond using real-world data - RAG pipelines, vector databases and semantic search, conversational agents with memory, and the observability tools to debug and optimize them.

AI developers, GenAI practitioners, Python developers and AI engineers who want to move beyond simple prompting to knowledge-aware AI systems.

It's an intermediate course, so you should be comfortable writing Python and have a basic idea of how LLMs are used. Course 1 of the specialization, Agent Foundations and Prompt Engineering, covers the groundwork if you need it.

Python with ChromaDB, Pinecone and FAISS for vector search, LangChain and LangGraph for workflows and agents, and LangSmith, LangFuse and OpenTelemetry for tracing and observability.

Coursera lists it at about 2 weeks at 10 hours a week, across 4 modules. It's fully self-paced, so you can spread it out around work.

Career & certificate

When you enroll in the course, you get access to all of the courses in the specialization, and you earn a certificate when you complete the work. Your electronic certificate is added to your Accomplishments page, where you can print it or add it to your LinkedIn profile.

Roles like AI Engineer, GenAI Developer, LLM Application Developer and Machine Learning Engineer - anywhere a team needs LLMs that work with its own data.

To access course materials and assignments and earn a certificate, you purchase the Certificate experience when you enroll. Eligible learners may be able to start with a free trial, and some may see a Full Course, No Certificate option.

Yes. In select learning programs you can apply for financial aid or a scholarship if you can't afford the enrollment fee. If it's available, you'll find a link to apply on the Coursera course page.

Want someone building this with you?

Board Infinity 1:1 coaching pairs you with a practitioner while you take the course.

See 1:1 coaching

Your first grounded agent is two weeks away.

Four modules. Fourteen assignments. RAG pipelines and agents you built yourself - and a certificate to show for it.

Enroll on Coursera

RAG Systems & Agentic Workflows with Pinecone and LangGraph · by Board Infinity · offered on Coursera

RAG Systems & Agentic Workflows Enroll