I use GitHub Copilot in Intellij with Claude Sonnet and the plan mode to implement complete features without me having to code anything.

I see it as a competent software developer but one that doesn't know the code base.

I will break down the tasks to the same size as if I was implementing it. But instead of doing it myself, I roughly describe the task on a technical level (and add relevant classes to the context) and it will ask me clarifying questions. After 2-3 rounds the plan usually looks good and I let it implement the task.

This method works exceptionally well and usually I don't have to change anything.

For me this method allows me to focus on the architecture and overall structure and delegate the plumbing to Copilot.

It is usually faster than if I had to implement it and the code is of good quality.

The game changer for me was plan mode. Before it, with agent mode it was hit or miss because it forced me to one shot the prompt or get inaccurate results.

▲

madcocomo 4 hours ago | parent | next [-]

My experience is that GitHub Copilot works much better in VS Code than Intellij. Now I have to open them together to work on one single project.

▲

hansmayer 9 hours ago | parent | prev [-]

Yeah, but what did you produce with it in the end? Show us the end result please.

▲

williamcotton 8 hours ago | parent | next [-]

I've been writing an experimental pipeline-based web app DSL with Claude Code for the last little while in my spare time. Sort of bash-like with middleware for lua, jq, graphql, handlebars, postgres, etc.

Here's an already out of date and unfinished blog post about it: https://williamcotton.com/articles/introducing-web-pipe

Here's a simple todo app: https://github.com/williamcotton/webpipe/blob/webpipe-2.0/to...

Check out the BDD tests in there, I'm quite proud of the grammar.

Here's my blog: https://github.com/williamcotton/williamcotton.com/blob/mast...

It's got an LSP as well with various validators, jump to definitions, code lens and of course syntax highlighting.

I've yet to take screenshots, make animated GIFs of the LSP in action or update the docs, sorry about that!

A good portion of the code has racked up some tech debt, but hey, it's an experiment. I just wanted to write my own DSL for my own blog.

▲

spreiti 9 hours ago | parent | prev [-]

I cannot show it because the code belongs to my employer.

▲

hansmayer 9 hours ago | parent [-]

Ah yes of course. But no one asked for the code really. Just show us the app. Or is it some kinda super-duper secret military stuff you are not even supposed to discuss, let alone show.

	▲	spreiti 35 minutes ago \| parent [-]
		It is neither of these. It's an application that processes data and is not accessible outside of the companies network. Not everything is an app. I described my workflow that has been a game changer for me, hoping it might be useful to another person because I have struggled to use LLMs for more than a Google replacement. As an example, one task of the feature was to add metrics for observability when the new action was executed. Another when it failed. My prompt: Create a new metric "foo.bar" in MyMetrics when MyService.action was successful and "foo.bar.failed" when it failed. I review the plan and let it implement it. As you can see it's a small task and after it is done I review the changes and commit them. Rinse and repeat. I think the biggest issue is that people try to one shot big features or applications. But it is much more efficient to me to treat Copilot as a smart pair programming partner. There you also think about and implement one task after the other.