Practical AI Tools: Machine Learning, Deep Learning, and RAG for Analysts and Non-Programmers

Training process

Training needs analysis

If you have specific requirements regarding the training programme, we will carry out a training needs analysis for you. This will guide us on which aspects of the programme should receive greater emphasis, so that the training programme meets your specific needs.

What will you gain?

You will understand how AI works - You will connect the dots between ML, deep learning, LLMs and generative models, so you can judge which AI approach actually fits a specific analytical task in your work.

You will speed up data analysis - You will learn how to use ChatGPT, Copilot and Gemini with Excel, SQL and BI to prepare data faster, summarize findings clearly and build an initial list of working hypotheses.

You will assess AI answers better - You will see where hallucinations, model errors and bias come from, and how to verify data quality so your analysis and business decisions are not based on misleading output.

You will build your own tools - You will practice describing a problem in a way that lets AI help you create templates, calculators, checklists, simple automations or useful queries for everyday analytical work.

You will use RAG in practice - You will understand how RAG works and how to prepare company documents and data for tools like NotebookLM or AnythingLM, so you can work with internal knowledge without coding.

You will spot good ML use cases - You will learn how to turn a business problem into prediction, classification or recommendation, define model inputs and outputs, and decide whether ML is worth using at all.

You will interpret model results - You will understand metrics such as accuracy, precision, recall and AUC in plain language, making it easier to compare models and explain what a prediction result really means.

You will choose the right AI tool - You will learn when a strong prompt or RAG is enough and when you need a classic predictive model or an AutoML solution, so you can avoid overcomplicating simple business tasks.

Training programme

1. How artificial intelligence works in practice

what modern AI „consists of”,
how the model generates a response,
where good responses come from,
basics of Machine Learning and Deep Learning:
- supervised learning, unsupervised learning, reinforcement learning (business examples: scoring, segmentation, recommendations),
- neural networks, deep networks, what distinguishes „classical” ML from Deep Learning,
how Machine Learning works „under the hood” for an analyst:
- data as the foundation of models: features, labels, the process of „learning from examples”,
- concepts: training, validation, test, overfitting, underfitting,
types of models: predictive, generative, LLMs:
- predictive models (regression, classification) in business tasks,
- generative models (text, images, code) vs „classical” predictive models,
- reasoning models.

2. AI in data analysis on a daily basis

supporting work in Excel,
preparation and description of data,
trend analysis and the first list of hypotheses,
typical scenarios for an analyst,
structured and unstructured data,
analytical tools with AI without programming – Copilot, ChatGPT, Gemini as an „AI layer” over Excel, SQL, BI,
tools of the type „data analysis with AI” in Excel/Power BI.

3. Can AI be trusted? Errors, biases and data quality in an analyst's work

hallucinations and errors – how to understand them,
biases (bias) in models and data,
data quality as a condition for meaningful analysis,
frameworks of trust: what AI can (not) be responsible for,
simple rules of „safe use” for the analyst.

4. Creating your own tools with the help of AI (extended with AutoML / no‑code)

how to describe a problem so that AI can design a tool,
file templates, calculators, checklists,
simple automations, macros, queries,
good practices in building „your own tools”,
AutoML and predictive models without programming,
low-code / no-code platforms for analysts,
AI-powered data analysis tools.

5. RAG systems and working with company data (NotebookLM, MS Notebooks, AnythingLM)

what RAG (Retrieval-Augmented Generation) is,
data for RAG: structured, unstructured, quality problems,
examples of using RAG without programming,
designing queries for RAG systems,
preparing data for working with RAG.

6. Fundamentals of Machine Learning in an analyst's practice

from the business problem to the model – how to recognize that this is an „task for ML”: prediction, classification, recommendation,
how to translate a business question into the model's input/output:
- life cycle of a simple ML project,
- understanding data, feature preparation, split into sets, quality assessment,
- metrics: accuracy, precision/recall, AUC in „human language”,
ML with the help of no-code tools:
- using AI for feature design, interpretation of model results, generation of descriptions and visualizations,
ML models vs. LLMs in an analyst's work:
- when to reach for a classic predictive model, and when it is enough,
- an LLM with a good prompt or RAG.

7. Creating your own tools with the help of AI

how to describe a problem so that AI can design a tool,
file templates, calculators, checklists,
simple automations, macros, queries,
best practices when building „your own tools”.

What are the prerequisites for participating in the training?

Basic data work skills - You should be comfortable working with tables, filtering, sorting and basic data cleanup, because the training focuses on practical analysis and real AI-supported workflows.

Familiarity with Excel or BI - You should know the basics of Excel, Power BI or a similar tool, so you can easily apply the examples from the course to your own reports, datasets and recurring analyses.

Analytical mindset - You should be able to frame business questions and draw conclusions from data, because during the training you will turn real problems into AI tasks and simple model goals.

Readiness to use AI tools - You should be willing to test new tools and ask precise questions, because the training includes hands-on work with AI assistants, RAG solutions and no-code platforms.