AI-Augmented Data Engineering, with Maksym Karashchuk

No Hallucinations: AI That Ships

AI-Augmented Data Engineering, with Maksym Karashchuk

2 giu 2026 · 29 min. 51 sec.

Capitoli

01 · Show intro and the five stages of AI in a data team

1 min. 24 sec.

02 · Why organisations slow down on adoption

3 min. 5 sec.

03 · Maksym's day now versus a year ago

3 min. 51 sec.

04 · Real agent examples: recordings vault, auto-documentation, the Azure DevOps loop

5 min. 7 sec.

05 · Human in the loop: the engineer verifies the pull request

7 min. 4 sec.

06 · The first time a machine opened the pull request for you

7 min. 58 sec.

07 · Adoption among peers and the blockers

8 min. 40 sec.

08 · Information overload and European governance on model inference

10 min. 50 sec.

09 · The guess machine: what you cannot trust an LLM with

12 min. 56 sec.

10 · Moving from wave one to wave two

13 min. 40 sec.

11 · Organisational readiness, BPMN, humans-with-agents versus agents-with-humans

14 min. 15 sec.

12 · The data warehouse homework an agent needs

15 min. 56 sec.

13 · Infrastructure, backend, and frontend as code

16 min. 32 sec.

14 · Generating project rules, garbage in garbage out

17 min. 24 sec.

15 · Where to store rules: Markdown and token economics

18 min. 41 sec.

16 · RAG versus Markdown, and why the vector database hallucinates more

19 min. 47 sec.

17 · Version control for the knowledge base

21 min. 36 sec.

18 · Treat rules like an architecture decision record

22 min. 13 sec.

19 · The role shift: from code repository to knowledge base and agents

23 min. 23 sec.

20 · Eighteen months out

24 min. 22 sec.

21 · Better models or better processes, and running Sonnet 4.6

25 min. 51 sec.

22 · Advice to data engineers: touch the technology, mind security

27 min. 4 sec.

23 · Will the data engineer job exist in ten years

28 min. 29 sec.

24 · Outro

29 min. 27 sec.

Descrizione

A data architect who builds agents every week gives an honest read on what AI is doing to the data engineering job. The job is not disappearing but it is...

mostra di più

A data architect who builds agents every week gives an honest read on what AI is doing to the data engineering job. The job is not disappearing but it is shifting: from writing code by hand to curating the rules, skills, and knowledge base that agents run on. As the LLMs are becoming commodity, the bottleneck in 2026 transitions form being a top model quality to the correctly built processes.

mostra meno

Commenti

Accedi per lasciare un commento

Informazioni

Autore	Astral Forest
Organizzazione	Astral Forest
Sito	-
Tag	#ai #analytics #architecture #astral forest #cdo #data #data leadership #datalake #datawarehouse #engineering #model #no hallucinations #podcast #reporting #technology