PrettyWhale.ai blog

Other articles

Data Engineering

Data Engineering Doesn't Need a Smarter AI Copilot

Every correction you type into a copilot is a requirement you already knew. Driving one means re-expressing your standards forever, one prompt at a time.

Data Engineering

Data Pipeline Vendor Lock-In Is Built One Connector at a Time

Lock-in is not a contract term, it is a rewrite estimate. Why the ingestion layer accumulates it faster than anything else, and how to measure yours today.

Artificial Intelligence

Small Language Models for Code Generation: When Narrow Beats Large

Small language models can match large ones on a bounded job like code generation, at 10 to 30 times lower serving cost. Here is when that trade holds.

Artificial Intelligence

Who Accepts AI-Generated Code That Nobody Wrote

Code review assumes an author who can answer for the code. Generated code breaks that assumption. What changes in the pull request, and after an incident.

Data Engineering

What "Production-Ready" Means for a Data Pipeline

Ask two engineers when an ingestion pipeline is finished and you get two answers. Here is how to write the bar down on one page and enforce it in review.

Data Engineering

Estimating Data Ingestion Work: A Unit-of-Work Method

Stop estimating ingestion tasks one by one. Estimate units of work, build a tier grid from your own delivery history, and recalibrate it after every project.

Partners

Moove-SI and PrettyWhale.ai Team Up on Data & AI

Moove-SI, an integrator specialising in Microsoft solutions, is adding PrettyWhale.ai to its Data & AI offer to speed up the costliest part of data projects.

Artificial Intelligence

Engineering AI, Copilots and Code Generators: A Taxonomy

"AI writes code now" covers four product families with four failure modes. The criterion that separates them, and four questions to pick the right one.

Data Engineering

The End of the Daily-Rate Model for IT Services

For thirty years IT services firms sold human time by the day. Clients now ask what you save them, not how many consultants you can put on the project.

Data Engineering

Ingestion vs Integration: A Confusion That Costs Millions

Ingestion and integration code get used as synonyms. They solve different problems, and the teams that optimise the wrong one pay for it in production.