I started using terminal coding agents around June last year. I used Claude Code for a few months, then switched to Opencode because the experience was rough. My terminal would constantly flicker, formatting was messy, and a single session could drag my whole machine down. Then after a month or two I moved to Pi and have been using it ever since.

What’s strange is that after going through all these coding agents, my workflow hasn’t really changed. It’s still very primitive. I ask a question or show agent some ideas, discuss the approach, let the agent write code, then I review and verify. I did try to adopt some of the “high-efficiency” workflows people talk about, but none of them work for me.

Around the end of last year I saw Boris, the Claude Code Author, share how he uses Claude Code. I was shocked. He runs multiple sessions in parallel. I tried to replicate that. It didn’t work. Two parallel sessions already feel like my limit. Once I go beyond that, my brain starts falling apart within minutes. Context switching is painful, I will lose myself in ten minutes.

Recently I saw another tweet from him, talking about how to use newer features in Claude Code. I realized I hadn’t even heard of half of them. I honestly feel like I’m falling behind

I wonder you guys really running multiple parallel sessions and using all these newer features effectively, and on top of that double your productivity? Or is this kind of workflow only realistic for a small group of people, like those building the tools themselves?

Comments URL: https://news.ycombinator.com/item?id=47573483

Points: 11

# Comments: 15

Comments URL: https://news.ycombinator.com/item?id=47386561

Points: 3

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=46645692

Points: 2

# Comments: 0

Do I need to explicitly tell Claude to read CLAUDE.md at the start of every session for it to consistently follow those preferences?

Often, it either generates convoluted implementations when simpler ones clearly exist, or it produces code that's riddled with bugs — despite confidently claiming it's correct. I'm wondering if I'm just not using it properly.

Here's my current workflow:

- I first talk to Gemini to gradually clarify and refine my requirements and design.

- I ask Gemini to summarize everything. Then I review and revise that summary.

- I paste the final version into Claude Code, use plan mode, and ask it to generate an implementation plan.

- I review the plan, make adjustments, and then let Claude Code execute it.

- Long wait…

- Review Claude’s output and clean up the mess.

For refactors and bugfixes, I usually write some tests in advance. But for new features, I often don’t.

It often feels like opening a loot box — 50% of the time it does a decent job, the other 50% is pretty bad. I really want to understand how to use it properly to achieve the kind of magical experience people describe.

Also, I’m on the Pro plan, and I rarely hit the rate limit — mainly because there’s a lot of prep work and post-processing I need to do manually. I’m curious about those who do hit rate limits quickly: are you running lots of tasks in parallel? Machines can easily parallelize, sure — but I don’t know how to make myself work in parallel like that.

Comments URL: https://news.ycombinator.com/item?id=44362244

Points: 19

# Comments: 16

However, I'm wondering:

Is the Agent SDK too abstracted or hard to debug?

Has anyone actually used it in a real production app yet?

Would I be better off just implementing the logic myself on top of the plain OpenAI SDK for more control and transparency?

Appreciate any insights.

Comments URL: https://news.ycombinator.com/item?id=44353964

Points: 8

# Comments: 3