I am feeling lucky again?
Evaluation metric became a tremendous help for me to measure and optimize the system. While doing it stumbling a metric MRR (Mean Reciprocal Rank) give me a light bulb “Hmm it’s similar with the google I am …
Read more
Archive
Notes and longer pieces from the blog.
Evaluation metric became a tremendous help for me to measure and optimize the system. While doing it stumbling a metric MRR (Mean Reciprocal Rank) give me a light bulb “Hmm it’s similar with the google I am …
Read more
I tried AI powered code review alongside SCA and SAST to see what it catches, where it helps, and how it might fit into our workflow.
Read more
Going back to basics with ReAct agent pattern taught me that most of the complexity is about handling a LLM output by parsing and adjusting prompt as to make sure the LLM output pattern matches what we expect while also …
Read more
Financial growth doesn’t mean that we became an expert overnight, understanding ourselves and patience is what we need to grow.
Read more
An exploration of how AI coding tools can make building feel less rewarding and more exhausting.
Read more
A practical account of finding low-effort cost optimizations before migrating workloads away from Amazon ECS.
Read more
Compare Amazon RDS gp2 and gp3 storage, including baseline IOPS, throughput, and migration considerations.
Read more
Set up a local Vagrant lab with Vault and LocalStack to practice for the HashiCorp Vault Associate certification.
Read more
How AWS WAF CAPTCHA challenges can help protect application endpoints from unwanted automated traffic.
Read more
A practical overview of using a Terraform-managed EC2 NAT instance as an alternative to AWS NAT Gateway.
Read more
Send CloudWatch alarm notifications to WhatsApp using Lambda and the Twilio SDK.
Read more