Oleksiy Kovyrin

The Problem Over the past year of building software across multiple companies and a ton of personal projects, I have noticed an uncomfortable reality: the more useful I wanted my agents to be for my work, the more access I needed to give them.

Earlier today, Nick Rempel mentioned in a tweet how important it is to set up tight feedback loops for AI agents when you’re working on something: Ive been using @cursor_ai heavily and I’ve developed a workflow that makes coding with LLMs way less painful.

After my last post on how the PRD->Tasklist->Work process I’ve been using for the past month has been instrumental for my being able to effectively context switch between a dozen different projects I have received a number of requests about the details of…

Another observation from using AI agents for multiple projects – at work and for a bunch of pet projects at home: The PRD → Tasklist → Work loop makes context switching surprisingly painless.

I’ve spent the last year turning large‑language‑model agents into productive teammates.

Someone, somewhere, is the person who pressed go on that software update.

This is my interview with Dr.

Today was my last day at Elastic.

This article has been originally posted on Swiftype Engineering blog.

Based on my experience, just a decade ago not many people within the Silicon Valley startup community considered compliance an important stepping stone in a company’s development roadmap.