Also I use intervals, I have basic analog timer, but I don't use pomorodo technique. If I'm in the flow state I can work much longer then originally intended without interruptions

- Setup proper CLAUDE.md or AGENTS.md

- Use cmux or conductor to manage multiple instances of Claude Code

When working of some business feature I always ask AI to summarize every conversation in following format: problem, brief solution, where change were made. And I store it in the repo under "journal" folder where each file has "2026-06-08-add-offile-firts-support.md"

Also for me personally having separate repository with some boilerplate code become a huge booster of productivity.

Usually inside this boilerplate repo I have:

- Descriptions of desired project structure, so every project follows the same structure I personally like

- Some CI/CD templates, in my case: build docker container, push into github registry, deploy to my bare bone VM

- Authentication + third parties integration

- Custom exceptions and middleware to handle those exceptions

- And more

Also quick question - what tool did you use to create such nice video/gif on your "hero" slide?

But you can apply the same logic for the software engineer, you take responsibility for the project you develop and lead. You take responsibility to make it work properly in different environments and load. What about software engineers who build software for the planes or rockets?

I think the biggest reason why most products and LLM provides still in negative because they are in the inception phase and trying to extend their market share.

Kind of similar to Uber when they spent huge amount of money to conquer new markets and increase their market share.

I think in the near future we will see significant increase of prices for tokens

Don't get me wrong, it still important, but I think understanding concepts and principles behind each application become more important

You still need to understand how database works and how to analyze performance, how to avoid N+1 problem. You still need to understand how to run your application in the cloud or some bare-bone vm. You still need to understand security concepts

I'm curious how do you manage them? Do you preserve them for the future or delete as soon as task was accomplished? If you're deleting those artifacts after job being done - do you summarize those specs into the Jira ticket or whatever system you use.

My problem is that most changelogs and news sources throw too much raw information at me. I spend a lot of effort going through it all just to figure out what actually matters. After a while I get overloaded, and then I give up and unsubscribe from everything.

So now I'm looking for more curated stuff. Maybe a newsletter, or some people who have a good point of view on software engineering and specific technologies. I want to follow people who filter the noise and explain the interesting parts well.

Right now my list is pretty short: - Hacker Newsletter - Platformer - The Pragmatic Engineer

What do you read? What newspapers are you subscribe to?

Comments URL: https://news.ycombinator.com/item?id=48414812

Points: 5

# Comments: 4

If I want do dig deeper - textbooks, white papers are still a good source.

Basically what I do:

- I have an idea of some architecture solution for the current task

- I try to sketch it myself and use AI to find some flaws I missing or try to find alternative approaches

- Review comments from AI and summarize into final decision

- Implement foundational layer myself or using AI to help me

- Document all crucial points like module boundaries, dependencies, key strutural elements

- Use AI to add features on top of newly built architecture

For me the biggest pain right now is to have some kind of central place where other team can post skills they use, prompts and other things. Right now we are thinking about creating a separate repo to store custom skills and other stuff so each team can contribute and use others team work.