LinkedIn
AT: +43 1 714 00 20 +43 1 714 00 20 DE: +49 69 348763610 +49 69 348763610 Mon-Fri 8am-5pm
Login Register

AI Agents and Automation

Certificate of attendance from Spirit in Projects Advanced

Would you like to get to know the next evolutionary stage of AI – autonomous agents that can independently plan tasks, make decisions and automate complex workflows? If you would like to understand how AI agents work and how you can develop them yourself using modern frameworks such as LangChain, CrewAI or AutoGPT, then look forward to this training. From the theoretical basics of agent architectures to practical implementation with current open source tools, you will learn how to develop intelligent automation solutions for your company.

Termine anzeigen Zurück zum Training
AI Expert

Ihre Lernziele

Understanding the basics of AI agents: definition, architecture, autonomy
Get to know different types of agents and their areas of operation
Developing LLM-based agents using ReAct paradigm
Master current open source frameworks (LangChain, CrewAI, AutoGPT)
Implement tool use and function calling for agents
Orchestrate multi-agent systems for complex tasks
Develop practical automation solutions with AI agents
Understand safety, evaluation and deployment strategies for agents

Zielgruppe

AI Expert Software developer ML engineer System Architect Software Architect DevOps Engineer Automation Specialist and anyone who wants to get involved with AI agents and intelligent automation

Kursinhalt

1 1. Basics of AI agents
  • What are AI agents?Definition and delimitation
  • From simple tools to autonomous systems
  • Agent vs. Model vs. Copilot
  • Autonomy and decision making
  • Perception, Action, Goal-Oriented Behavior
  • Agent-environment interaction
  • Historical development: From rule-based to LLM-based agents
  • Current trends: Growing importance of AI agents in enterprise applications
2 2. Agent architectures
  • Reactive Agents: Stimulus-Response
  • Deliberative Agents: Planning and Reasoning
  • Hybrid Architectures
  • BDI model: Beliefs, Desires, Intentions
  • Layered Architectures
  • Subsumption Architecture
  • Comparison and application scenarios
3 3. Agent scheduling algorithms
  • Goal-based planning
  • Utility-based planning
  • State Space Search
  • Forward vs backward planning
  • Hierarchical Task Networks (HTN)
  • Planning algorithms in practice
4 4. Reinforcement learning for agents
  • Basics of Reinforcement Learning
  • Markov Decision Processes (MDP)
  • Q-Learning and Deep Q-Networks (DQN)
  • Policy gradient methods
  • Multi Armed Bandits
  • RL for autonomous agents
5 5. LLM based agents
  • Revolution through Large Language Models
  • LLMs as Reasoning Engines
  • ReAct paradigm: Reasoning + Acting
  • Observation, Thought, Action Loop
  • Chain-of-thought for agents
  • Tree-of-Thought for complex decisions
  • Self-reflection and self-correction
6 6. Tool Use and Function Calling
  • Concept of tool use in LLMs
  • Function Calling: OpenAI, Anthropic, Google approaches
  • Tool description and schemas
  • Multi-tool orchestration
  • Connect external APIs: Web Search, Calculator, Database
  • Error handling and retry strategies
  • Practical Exercise: Multi-Tool Agent (Google Colab)
7 7. Memory and context management
  • Short-term vs. long-term memory
  • Conversation history management
  • Memory Types: Buffer, Summary, Entity, Knowledge Graph
  • Vector databases as long-term memory
  • Context window optimization
  • Practical exercise: Agent with memory system
8 8. LangChain for agents
  • Overview of LangChain Framework
  • Agents in LangChain: Zero-shot, Conversational, ReAct
  • Tools and toolkits
  • Chains vs Agents
  • AgentExecutor and Agent Types
  • Custom tool development
  • LangSmith for agent debugging
  • Practical exercise: ReAct agent with LangChain (Google Colab)
9 9. LlamaIndex for Data Agents
  • LlamaIndex basics
  • Data Agents for RAG workflows
  • Query engines and data connectors
  • Multi-Document Agents
  • Integration with vector databases
  • Practical exercise: RAG agent with LlamaIndex
10 10. Autonomous Agents: AutoGPT and BabyAGI
  • Autonomous task execution concept
  • AutoGPT: Architecture and functionality
  • BabyAGI: Task-driven Autonomous Agent
  • Task decomposition and prioritization
  • Iterative task planning and self-critique
  • Limitations and challenges
  • Practical exercise: Autonomous Research Agent (Google Colab)
11 11. Multi-agent systems
  • Why multi-agent systems?
  • Agent communication and coordination
  • Role-based agent design
  • Collaborative vs Competitive Agents
  • Consensus and negotiation
  • Task distribution and load balancing
12 12. CrewAI for Multi-Agent Orchestration
  • Overview of CrewAI Framework
  • Crews, agents, tasks, tools
  • Role-based agent definition
  • Process Types: Sequential, Hierarchical, Consensual
  • Agent Delegation and Collaboration
  • Output handling and result aggregation
  • Practical exercise: Multi-agent system with CrewAI (Google Colab)
13 13. Cost optimization
  • Minimize token usage among agents
  • Caching strategies
  • Model selection: High end models vs. low end vs. open source
  • Routing: Simple tasks to cheaper models
  • Batching and parallelization
  • Cost monitoring and budget alerts

Certification

For this training you will receive a certificate of participation from Spirit in Projects.

Mehr zu Zertifizierungen

Nach dem Kurs empfehlen wir

Computer Vision and Generative AI
AI Testing (Testing of AI-based Systems)

Kurs auf einen Blick

  • Certification Certificate of attendance from Spirit in Projects
  • Level Advanced
  • Dauer 2 days
  • Preis EUR 1,490.-- excl. VAT
Termine anzeigen

Certified trainings

Internationally recognized certifications for your career.

Experienced trainers

Lernen Sie von kompetenten Experten mit Praxiserfahrung.

Flexible formats

Webinars, video trainings or on-site – entirely according to your needs.