Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Overview of Large Language Model Agent Systems
- Concepts underlying LLM agents and multi-agent architectures
- Introduction to the AutoGen framework and its associated ecosystem
- Agent roles, including user proxy, assistant, function caller, and others
Installation and Configuration of AutoGen
- Establishing the Python environment and required dependencies
- Fundamentals of AutoGen configuration files
- Integration with LLM providers (OpenAI, Azure, and local models)
Agent Design and Role Assignment
- Understanding agent types and interaction patterns
- Defining agent objectives, prompts, and operational instructions
- Task delegation and control flow based on agent roles
Function Calling and Tool Integration
- Registering functions for use by agents
- Supporting autonomous and collaborative function execution
- Linking external APIs and Python scripts to agent capabilities
Conversation Management and Memory
- Session tracking and persistent memory storage
- Agent-to-agent messaging and token management
- Maintenance of conversation context and history
End-to-End Agent Workflows
- Development of multi-step collaborative tasks (e.g., document analysis, code review)
- Simulation of user-agent dialogues and decision processes
- Debugging and optimization of agent performance
Use Cases and Deployment for government
- Internal automation agents: research, reporting, scripting
- External-facing applications: chat assistants, voice integrations
- Packaging and deploying agent systems in production environments
Summary and Next Steps
Requirements
- Proficiency in Python development
- Knowledge of large language models and prompt design techniques
- Practical application of APIs and automated processes
Target Participants
- AI engineers
- Machine learning developers
- Automation architects
21 Hours
Testimonials (1)
I liked that he constantly provided examples but also offered time for individual work on what he presented.