AI in data engineering must not become a magic layer above the pipeline. It should help with design, checks, and documentation while keeping the result repeatable and defensible.
Basics
- Length: 2 days (2 × 8 hours)
- Price: from 18 000 CZK / participant / day (ex-VAT)
- Format: on-site, adapted to your data stack, on demand
- Max participants: 15
- Who it's for: data engineers, analysts, BI teams, platform teams, and tech leads
- Prerequisites: familiarity with your data flows, ETL/ELT, or BI environment
What you'll take away
- A way to use AI when designing pipelines, transformations, and data contracts.
- Review prompts for data quality, edge cases, and documentation.
- Rules for reproducibility, versioning, and audit trails.
- A practical AI-assisted data change from requirement to review.
- A list of places where AI does not belong without additional safeguards.
Program
Day 1: design and data understanding
- Map existing data flows and recurring pain points.
- Use AI to read schemas, documentation, and transformation logic.
- Draft a data contract and checks against business rules.
- Identify sensitive data and boundaries for AI usage.
Day 2: quality, operations, and governance
- Generate tests and checks for data transformations.
- Document pipeline logic and lineage with AI assistance.
- Review a change: what AI checks and what must stay with people.
- Operating rules: audit, logging, reproducibility, approvals.
- Team playbook for the first month of usage.
How it fits
If the team builds AI applications on top of data, continue with Azure AI Foundry, RAG & Copilot Studio. For business reporting, use Data Chat: Power BI + AI.
Want this training for your team?
Every training is tailored to your team. Tell us about your people, stack, and goals, and we'll come back with a concrete proposal.
Want to stay one step ahead?
Don't miss our best insights. No spam, just practical analyses, invitations to exclusive events, and podcast summaries delivered straight to your inbox.