Tue
21
Oct
Events
Tech Talk DATA REPLY - Large Language Models, Autonomous Agents, and Applied AI
Data Reply is the Reply Group company that redesigns the future through excellence in Data, Artificial Intelligence, and Quantum Computing services. It supports C-level executives and their teams in extracting real business value from data, operating across various industries and business functions. The company develops complete data-driven solutions, from data strategy to production deployment.
It is committed to enabling and rethinking new data-based business models and strategies through Analytics, Machine Learning, and Intelligent Process Automation, while integrating the opportunities offered by Generative AI.
The Tech Talk aims to explore the evolution of applications based on Large Language Models (LLMs) towards more complex architectures built on autonomous AI agents. The session will analyze changes in design, technology, and operational paradigms, focusing specifically on how this transition impacts not only application logic but also integration, orchestration, and observability processes in production environments.
The agenda will include a technical overview of the differences between traditional LLM-based solutions (e.g., prompt-based, retrieval-augmented generation) and agent-based solutions (multi-step reasoning, task delegation, interaction between multiple intelligent components).
Main objectives:
To participate, registration is required by October 20th AT THIS LINK.
The event will be held in Italian.
--------------------------------------------------------------------------------------------------------------
SAVE THE DATE
Tech Talk DATA REPLY – Large Language Models, Autonomous Agents and Applied AI
When: October 21st, 2:30 PM modified schedule
Where: Classroom 4M
Who: The event is dedicated to graduates and master’s students in Data Science, Computer Engineering, Mathematical Engineering, Quantum Engineering, and PhD students in Computer and Systems Engineering or Artificial Intelligence – participation is also open to individuals with related backgrounds.
It is committed to enabling and rethinking new data-based business models and strategies through Analytics, Machine Learning, and Intelligent Process Automation, while integrating the opportunities offered by Generative AI.
The Tech Talk aims to explore the evolution of applications based on Large Language Models (LLMs) towards more complex architectures built on autonomous AI agents. The session will analyze changes in design, technology, and operational paradigms, focusing specifically on how this transition impacts not only application logic but also integration, orchestration, and observability processes in production environments.
The agenda will include a technical overview of the differences between traditional LLM-based solutions (e.g., prompt-based, retrieval-augmented generation) and agent-based solutions (multi-step reasoning, task delegation, interaction between multiple intelligent components).
Main objectives:
- Provide a clear overview of the technical evolution from LLMs to AI agents.
- Highlight the advantages in terms of flexibility, autonomy, and scalability.
- Discuss operational implications: logging, tracing, A/B testing, fallback mechanisms, security, and agent lifecycle management.
- Encourage discussion on emerging tools and frameworks, and on the opportunity to standardize new DevOps/LLMOps practices.
To participate, registration is required by October 20th AT THIS LINK.
The event will be held in Italian.
--------------------------------------------------------------------------------------------------------------
SAVE THE DATE
Tech Talk DATA REPLY – Large Language Models, Autonomous Agents and Applied AI
When: October 21st, 2:30 PM modified schedule
Where: Classroom 4M
Who: The event is dedicated to graduates and master’s students in Data Science, Computer Engineering, Mathematical Engineering, Quantum Engineering, and PhD students in Computer and Systems Engineering or Artificial Intelligence – participation is also open to individuals with related backgrounds.