AIcademy
Using Generative AI Models & Systems Effectively
Introduction
This session provides an in-depth look at the workings and applications of generative AI systems such as ChatGPT , Gemini , Claude and LLaMA . In contrast to the knowledge session on Large Language Models (LLMs), this training focuses on more advanced concepts and technical aspects , such as transformer architecture, model context, evaluation methods and integration options.
You will learn how generative models work, how to assess their output, and which approach — prompt engineering, fine-tuning, or RAG — is best suited for different use cases. We will also consider reliability, risk, and governance for large-scale deployment of generative AI in organizations.
Learning objectives
1. Understand how generative AI models work
Transformers Architecture and the Importance of Self-Attention
How tokens , embeddings and context windows work
Understanding training data, model size, and fine-tuning methods
2. Evaluate and assess output
Assess output on:
Factuality – is the generated information correct?
Bias – are there any biases visible in the model?
Consistency – is the output logical and consistent?
Helpfulness – is the output relevant and useful?Difference between human evaluation and automatic scoring methods
3. Customization and integration techniques
Prompt engineering – controlling output via smart input
Fine-tuning – adapting models to specific domains or tasks
Retrieval-Augmented Generation (RAG) – Linking LLMs to your own documentation or knowledge bases
Trade-offs between flexibility, costs, control and maintenance
4. Responsible and strategic use of generative AI
Risk Insight: Hallucinatory Output, Misinterpretation, Dependence
Governance: documentation, auditing, monitoring and policy frameworks
Legal and ethical frameworks: AI Act , GDPR , transparency requirements
Practical tips for responsible implementation in organizational processes
For whom
This session is intended for AI specialists, data leads, technical decision makers, innovation advisors and architects who want to deploy generative AI strategically and responsibly — and want to gain more insight into the technical operation, evaluation and integration of these systems within their organization.
Interested in this session?
Feel free to contact us. We are happy to think along with you about a solution that fits your team, sector and technological context.
Using Generative AI Models & Systems Effectively
Introduction
This session provides an in-depth look at the workings and applications of generative AI systems such as ChatGPT , Gemini , Claude and LLaMA . In contrast to the knowledge session on Large Language Models (LLMs), this training focuses on more advanced concepts and technical aspects , such as transformer architecture, model context, evaluation methods and integration options.
You will learn how generative models work, how to assess their output, and which approach — prompt engineering, fine-tuning, or RAG — is best suited for different use cases. We will also consider reliability, risk, and governance for large-scale deployment of generative AI in organizations.
Learning objectives
1. Understand how generative AI models work
Transformers Architecture and the Importance of Self-Attention
How tokens , embeddings and context windows work
Understanding training data, model size, and fine-tuning methods
2. Evaluate and assess output
Assess output on:
Factuality – is the generated information correct?
Bias – are there any biases visible in the model?
Consistency – is the output logical and consistent?
Helpfulness – is the output relevant and useful?Difference between human evaluation and automatic scoring methods
3. Customization and integration techniques
Prompt engineering – controlling output via smart input
Fine-tuning – adapting models to specific domains or tasks
Retrieval-Augmented Generation (RAG) – Linking LLMs to your own documentation or knowledge bases
Trade-offs between flexibility, costs, control and maintenance
4. Responsible and strategic use of generative AI
Risk Insight: Hallucinatory Output, Misinterpretation, Dependence
Governance: documentation, auditing, monitoring and policy frameworks
Legal and ethical frameworks: AI Act , GDPR , transparency requirements
Practical tips for responsible implementation in organizational processes
For whom
This session is intended for AI specialists, data leads, technical decision makers, innovation advisors and architects who want to deploy generative AI strategically and responsibly — and want to gain more insight into the technical operation, evaluation and integration of these systems within their organization.
Interested in this session?
Feel free to contact us. We are happy to think along with you about a solution that fits your team, sector and technological context.
Description:
Learn about the operation, architecture and evaluation of generative AI models such as ChatGPT, Gemini and LLaMA.
Learning objectives:
Understand how LLMs work: transformers, tokens, embeddings and context.
Methods to evaluate the output of LLMs: factuality, bias, consistency, helpfulness.
Understanding methods to detect hallucinations
Gain knowledge of the different types of LLMs, such as reasoning and multimodal models.
Insights into prompt engineering vs. fine-tuning vs. RAG for specific use cases.
For whom: Engineers and technical professionals who really want to understand how Generative AI systems work.
Using Generative AI Models & Systems Effectively
Introduction
This session provides an in-depth look at the workings and applications of generative AI systems such as ChatGPT , Gemini , Claude and LLaMA . In contrast to the knowledge session on Large Language Models (LLMs), this training focuses on more advanced concepts and technical aspects , such as transformer architecture, model context, evaluation methods and integration options.
You will learn how generative models work, how to assess their output, and which approach — prompt engineering, fine-tuning, or RAG — is best suited for different use cases. We will also consider reliability, risk, and governance for large-scale deployment of generative AI in organizations.
Learning objectives
1. Understand how generative AI models work
Transformers Architecture and the Importance of Self-Attention
How tokens , embeddings and context windows work
Understanding training data, model size, and fine-tuning methods
2. Evaluate and assess output
Assess output on:
Factuality – is the generated information correct?
Bias – are there any biases visible in the model?
Consistency – is the output logical and consistent?
Helpfulness – is the output relevant and useful?Difference between human evaluation and automatic scoring methods
3. Customization and integration techniques
Prompt engineering – controlling output via smart input
Fine-tuning – adapting models to specific domains or tasks
Retrieval-Augmented Generation (RAG) – Linking LLMs to your own documentation or knowledge bases
Trade-offs between flexibility, costs, control and maintenance
4. Responsible and strategic use of generative AI
Risk Insight: Hallucinatory Output, Misinterpretation, Dependence
Governance: documentation, auditing, monitoring and policy frameworks
Legal and ethical frameworks: AI Act , GDPR , transparency requirements
Practical tips for responsible implementation in organizational processes
For whom
This session is intended for AI specialists, data leads, technical decision makers, innovation advisors and architects who want to deploy generative AI strategically and responsibly — and want to gain more insight into the technical operation, evaluation and integration of these systems within their organization.
Interested in this session?
Feel free to contact us. We are happy to think along with you about a solution that fits your team, sector and technological context.
How It All Started
This is a space to share more about the business: who's behind it, what it does and what this site has to offer. It's an opportunity to tell the story behind the business or describe a special service or product it offers. You can use this section to share the company history or highlight a particular feature that sets it apart from competitors.
Let the writing speak for itself. Keep a consistent tone and voice throughout the website to stay true to the brand image and give visitors a taste of the company's values and personality.