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. The program is designed and delivered by practitioners with real-world experience.
What you will 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 learned concepts in your organization. After completing the training, you will have actionable knowledge that translates directly into improved capabilities for your team and organization.
Benefits
- Understand and apply agentic ai
- Design and implement solutions based on best practices
- Evaluate tools and approaches
- Build implementation roadmap
- Integrate with existing processes
- Measure and optimize outcomes
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
Architektura systemów agentowych — od chatbota do autonomicznego agenta
- Ewolucja AI: chatbot vs copilot vs agent vs multi-agent system
- Wzorce architektoniczne: ReAct, Plan-and-Execute, Reflexion
- Anatomia agenta: LLM + tools + memory + planning
- Kiedy agent a kiedy pipeline — decyzje architektoniczne
- Przegląd frameworków: LangGraph, CrewAI, AutoGen, OpenAI Agents SDK
- Bezpieczeństwo i guardrails dla autonomicznych agentów
LangGraph — budowanie agentów jako grafów stanów
- LangGraph vs LangChain: kiedy który framework
- State machines i cykle w LangGraph
- Nodes, edges i conditional routing
- Human-in-the-loop: approval gates i interrupts
- Persistence i checkpointing — odporność na błędy
- Streaming i real-time output z agentów LangGraph
CrewAI — zespoły agentów z podziałem ról
- Architektura CrewAI: Agents, Tasks, Crews, Processes
- Definiowanie ról, celów i backstory agentów
- Task delegation i hierarchia agentów
- Sequential vs hierarchical vs consensual processes
- Custom tools i integracje zewnętrzne
- Warsztaty: budowanie zespołu agentów do analizy rynku
Tool use, function calling i integracje zewnętrzne
- Function calling w OpenAI, Anthropic i open-source LLM
- Projektowanie tool schemas — best practices
- Budowanie custom tools: API, bazy danych, file system, web scraping
- MCP (Model Context Protocol) — standard integracji narzędzi
- Error handling i retry logic w tool use
- Bezpieczeństwo tool use — sandboxing i permission control
Memory i kontekst — jak agent pamięta i uczy się
- Short-term memory: conversation buffer i sliding window
- Long-term memory: vector store i knowledge graph
- Episodic memory: uczenie się z poprzednich wykonań
- Shared memory w systemach multi-agent
- RAG jako memory backend dla agentów
- Optymalizacja kontekstu — prompt compression i summarization
Multi-agent orchestration i deployment produkcyjny
- Wzorce multi-agent: supervisor, swarm, debate, marketplace
- Komunikacja między agentami: message passing vs shared state
- Monitoring i observability agentów (LangSmith, Langfuse)
- Testowanie agentów: evaluation frameworks i benchmarki
- Deployment: containerization, scaling, cost management
- Case studies: agenty produkcyjne w 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?
This training is at advanced. Check prerequisites above.
What practical exercises are included?
Hands-on exercises in prepared lab environment with realistic scenarios.
Will I receive a certificate?
Yes — EITT certificate of completion plus comprehensive materials.
Why choose EITT?
500+ experts, 2500+ trainings, 4.8/5 rating. Practitioners with real-world experience.
Request a quote
Funding Options
Check funding options for your company
Development Services Database
Up to 80% funding for SMEs from EU funds
Check availabilityNational Training Fund
Up to 100% funding for employers
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.