Applied AI#024
Applied AI8 min
AI in production: RAG, evals and prompt injection
Anybody can build a demo that impresses. What separates the demo from the product is three disciplines, and most teams have none of them.
ragevalsllm-as-judge
Software engineering and applied AI
What happens when the code leaves the laptop and meets a real user.
I am Gabriel Dias. I work on payment infrastructure and production AI systems at Woovi. Here I write about the boring decisions nobody covers in tutorials: the ones that show up at 3am, with users waiting.
- published articles
- 24
- categories
- 2
- writing code since
- 2016
Library
Latest writing
Reading path
22 articles in learning order.
Engineering#023
Engineering7 min
Data and analytics: from OLTP to lakehouse
Two questions come up in every company: why did the report take down production, and why is the number on my dashboard different from yours. Both have the same root cause.
oltpolapcolumnar
Applied AI#022
Applied AI5 min
What changes when the AI agent leaves the laptop
The demo works in five minutes. What nobody shows is the evaluation, cost and failure layer that separates a prototype from something a real user can survive.
llmagentsevaluation
Engineering#021
Engineering7 min
Legacy: characterise, seam and strangle
Three techniques that let you safely change a system you did not write, do not understand, and cannot stop.
legacy-codecharacterisation-testsgolden-master
Engineering#020
Engineering6 min
Tests worth what they cost
Tests do not exist to prove the code is right. They exist so you can change it tomorrow without fear. That change of goal reorganises everything.
testingtest-pyramidmocks
Talk to me
Questions about the article? Message me on WhatsApp
No form and no mailing list. If you disagree with something I wrote, or want to tell me how you solved it, the conversation goes straight to me.