Tag archive
On March 12, 2025, during a migration of Project Orions retrieval-augmented pipeline, the production...
As a Senior Solutions Architect running the conversational layer for a high-traffic commerce app, the...
On 2026-03-14, during a high-traffic deploy of our consumer chat product, the moderation and reply...
As a Principal Systems Engineer, this is a targeted deconstruction: peel away the glossy claims about...
Many teams ship a capable model into production and watch it degrade under real traffic, unexpected...
On a migration for a fintech startup I help with, a recurring decision kept appearing in...
The post-mortem started with an alert that well never forget: latency went through the roof, a core...
On March 12, 2026 I was knee-deep in a side project: a small assistant that summarizes long design...