Agentic AI — Building Autonomous Agents with LangGraph and CrewAI
Advanced training on building autonomous AI agents. Covers agentic system architecture, LangGraph (state machines, cycles, human-in-the-loop), CrewAI (role-based agents, task delegation), tool use and function calling, memory (short-term, long-term, episodic), multi-agent orchestration, and production agent deployment.
Why choose this training?
Advanced training on building autonomous AI agents. Covers agentic system architecture, LangGraph (state machines, cycles, human-in-the-loop), CrewAI (role-based agents, task delegation), tool use and function calling, memory (short-term, long-term, episodic), multi-agent orchestration, and production agent deployment. This training combines theoretical knowledge with intensive hands-on exercises, enabling participants to immediately apply their skills in daily work.
What will you learn?
You will gain comprehensive knowledge and practical skills in agentic AI. The program covers all key aspects — from foundational concepts, through advanced techniques, to real-world implementation patterns.
Through hands-on exercises and realistic scenarios, you will develop the ability to apply the concepts you learn in the context of your organization. After completing the training, you will have knowledge ready for immediate application.
Benefits
- Understand and apply agentic AI
- Design and implement solutions based on best practices
- Evaluate tools and approaches
- Build an implementation roadmap
- Integrate with existing processes
- Measure and optimize results
Who is this training for?
Prerequisites
- IT experience or domain expertise
- Basic understanding of AI concepts is helpful
- Willingness to learn and experiment
Training program
Agentic System Architecture — From Chatbot to Autonomous Agent
- The evolution of AI: chatbot vs copilot vs agent vs multi-agent system
- Architectural patterns: ReAct, Plan-and-Execute, Reflexion
- Anatomy of an agent: LLM + tools + memory + planning
- When to use an agent and when a pipeline — architectural decisions
- Framework overview: LangGraph, CrewAI, AutoGen, OpenAI Agents SDK
- Security and guardrails for autonomous agents
LangGraph — Building Agents as State Graphs
- LangGraph vs LangChain: when to use which framework
- State machines and cycles in LangGraph
- Nodes, edges and conditional routing
- Human-in-the-loop: approval gates and interrupts
- Persistence and checkpointing — fault tolerance
- Streaming and real-time output from LangGraph agents
CrewAI — Agent Teams with Role Division
- CrewAI architecture: Agents, Tasks, Crews, Processes
- Defining agent roles, goals and backstories
- Task delegation and agent hierarchy
- Sequential vs hierarchical vs consensual processes
- Custom tools and external integrations
- Workshop: building an agent team for market analysis
Tool Use, Function Calling and External Integrations
- Function calling in OpenAI, Anthropic and open-source LLMs
- Designing tool schemas — best practices
- Building custom tools: APIs, databases, file system, web scraping
- MCP (Model Context Protocol) — a standard for tool integration
- Error handling and retry logic in tool use
- Tool use security — sandboxing and permission control
Memory and Context — How an Agent Remembers and Learns
- Short-term memory: conversation buffer and sliding window
- Long-term memory: vector store and knowledge graph
- Episodic memory: learning from previous runs
- Shared memory in multi-agent systems
- RAG as a memory backend for agents
- Context optimization — prompt compression and summarization
Multi-Agent Orchestration and Production Deployment
- Multi-agent patterns: supervisor, swarm, debate, marketplace
- Inter-agent communication: message passing vs shared state
- Agent monitoring and observability (LangSmith, Langfuse)
- Testing agents: evaluation frameworks and benchmarks
- Deployment: containerization, scaling, cost management
- Case studies: production agents in the enterprise
Delivery Methods
Online
- Convenience of participating from anywhere
- Interactive live sessions with trainer
- Materials available for 30 days
- No travel costs
On-site
- Direct contact with trainer and group
- Intensive hands-on workshops
- Networking with other participants
- Full focus on learning
Frequently asked questions
Is this training suitable for my level?
The training is at an advanced level. Check the prerequisites above.
What practical exercises are included in the program?
Hands-on exercises in a prepared lab environment with realistic scenarios.
Will I receive a certificate?
Yes — an EITT certificate of completion plus comprehensive training materials.
Why EITT?
Over 2,500 trainings in our catalog. Practitioners with experience in real-world projects.
Request a quote
Funding Options
Check funding options for your company
Development Services Database
An instrument for micro, small and medium-sized companies — check whether it applies to your organisation
Check availabilityNational Training Fund
An instrument for employers — we help you check whether it can be applied
Learn moreTrusted by
We train teams at Poland's largest companies
Interested in this training?
Contact us - we'll prepare an offer tailored to your organization's needs.