Building and Deploying AI Agents with LLMs and LangChain

Board Infinity via Coursera Specialization

Go to class Write review

Details

Go to class

Provider

Coursera Specialization
Pricing

Paid Course
Languages

English
Certificate

Certificate Available
Level

Intermediate

Found in

Overview

Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off

One annual plan covers every course and certificate on Coursera. 40% off for a limited time.

Get Full Access

This three-course specialization guides AI practitioners and developers through the complete journey of building practical AI agent systems — from single-agent architecture to multi-agent collaboration to production deployment. You will master modular agent design using LangGraph for graph-based workflows, Pydantic-AI for structured validation, and Mem0 for persistent memory, building agents that perceive, reason, and act across real-world scenarios. As you progress, you will design multi-agent collaboration systems using CrewAI and Agno — defining planner, executor, reviewer, and critic roles with shared memory and communication patterns. The final course brings everything together by integrating LLMs from OpenAI and Anthropic into orchestrated workflows, adding production-ready state management, deploying via FastAPI, and implementing monitoring and evaluation pipelines. By the end, you will be able to architect, coordinate, and deploy multi-agent systems integrated with external APIs for enterprise automation.

Syllabus

Course 1: AI Agent Architecture: Reasoning, Memory, and LangGraph
Course 2: Designing Multi-Agent Systems: Collaboration and Workflows
Course 3: Deploying AI Agents: LLMs, LangGraph, and Production APIs

Courses

0 reviews

View details

"Architecting AI Agents for Real-World Systems is a hands-on course designed for developers, AI engineers, and technical professionals who want to build production-grade agentic AI systems using LangGraph, Mem0, and Pydantic-AI. You'll learn how to design modular agent architectures, implement structured I/O, add persistent memory, and evaluate frameworks for real deployment. Module 1 introduces the foundations of agentic AI, covering the perception–reasoning–action lifecycle, modular vs. monolithic design, and graph-based reasoning with LangGraph. Module 2 focuses on building structured and reliable agents, using Pydantic-AI for schema validation and LangGraph for workflow orchestration, culminating in an Email-to-Task agent. Module 3 explores memory and persistence, where you'll implement Mem0 to give your agents short-term, long-term, and contextual memory, then benchmark recall and performance. Module 4 integrates all components into a functional Research Assistant Agent and compares LangGraph, LangChain, and Agno for production readiness. By the end of this course, you will: - Design modular agent workflows using LangGraph nodes and edges - Implement structured I/O validation with Pydantic-AI - Add persistent memory to agents using Mem0 - Evaluate and select the right agentic framework for real-world deployment"
0 reviews

View details

"Take your AI agent skills into production with this hands-on course on building, validating, and deploying LLM-powered agents using LangGraph, LangChain, Pydantic-AI, Mem0, CrewAI, Agno, and FastAPI. You’ll learn to turn prototypes into reliable, enterprise-grade agent systems. Module 1 covers integrating LLMs (OpenAI, Anthropic) into LangGraph reasoning pipelines, designing nodes, control flow, token management, and iterative workflow testing. Module 2 focuses on schema enforcement with Pydantic-AI, structured outputs, and building a Business Workflow Assistant with validated, reliable I/O. Module 3 guides you through full deployment — FastAPI backends, persistent memory with Mem0 and vector stores, and orchestration with Agno and CrewAI in production. Module 4 teaches evaluation: metrics, logging, load testing, benchmarking, and comparing LangGraph, CrewAI, and Agno for enterprise-scale deployment. By the end of this course, you will: - Integrate LLMs into modular LangGraph reasoning pipelines - Validate agent I/O using Pydantic-AI schemas for reliable outputs - Deploy agents via FastAPI with Mem0 and vector-store persistence - Evaluate and benchmark frameworks to justify production choices"
0 reviews

View details

"Master the design and orchestration of collaborative AI systems in this hands-on course on multi-agent workflows using CrewAI, Agno, Mem0, AutoGen, and LangGraph. You’ll learn how to move beyond single-agent prompting to build teams of coordinated AI agents that plan, execute, and review complex tasks together. Module 1 introduces the foundations of multi-agent coordination, role hierarchies (Planner, Executor, Reviewer), and the CrewAI framework for agent orchestration. Module 2 guides you through designing role-based workflows, implementing a Researcher–Writer–Editor content team, and analyzing coordination efficiency using CrewAI logs and metrics. Module 3 focuses on shared and private memory models using Mem0, covering context hand-off, synchronization, and memory performance tuning for multi-agent pipelines. Module 4 explores advanced orchestration with Agno, a real-world Customer Support automation case study, and comparative benchmarking of CrewAI, AutoGen, and LangGraph. By the end of this course, you will: - Build and orchestrate multi-agent workflows using CrewAI and Agno - Integrate shared memory with Mem0 for context-aware collaboration - Design role-based pipelines simulating human-style teamwork - Compare leading frameworks to choose the right stack for production"