Ask HN: Do you have any evidence that agentic coding works?

Everyone is using Cursor, model preference varies. The best performers have large context in their repository, make very detailed plans using Planning mode and then execute. Use different models to individually review the work.

I obviously don't know that my past two days of work would have taken two weeks in the alternative route, but it's my feeling for this particular work:

I'm implementing a drawing tool on top of maps for fire departments (see demo.syncmap.no -- it's only in Norwegian for now though, plan to launch in English and Show HN it in some months). Typescript, Svelte, Go, Postgres.

This week I have been making the drawing tools more powerful (not deployed publicly yet).

* Gesture recognition to turn wobbly lines into straight lines in some conditions

* Auto-fill closed shapes: Vector graphics graph algorithms to segment the graph and compute the right fill regions that feel natural in the UI (default SVG fill regions were not right, took some trial and error to find something that just feels natural enough)

* Splines to make smoother curves .. fitting Catmull-Rom, converting those to other splines for SVG representation etc

* Constraints when dragging graph nodes around that shapes don't intersect when I don't want them to etc

I haven't been working all that much with polygon graphics before, so the LLM is very helpful in a) explaining me the concepts and b) providing robust implementations for whatever I need.

And I've had many dead ends that didn't feel natural in UI that I could discard after trying them out in full, without loosing huge investment.

These are all things that are very algorithm and formula intensive and where I would have had do to a lot of reading and research to do things right myself. (I could deal with it, but it takes a lot of time to read up on it.)

I review to see that it "looks sensible", not every single addition and division in the spline interpolations, or every step of the graph segmentation algorithms used to compute fill regions. I review function signatures and overall architecture, not the small details (in frontend -- obviously the backend authorization code is reviewed line by line..)

I code powershell, and what really worked for me was defining a highly detailed and specific rules file that outlines exactly what kind of output I want. This includes coding style, design patterns, example function structure, and a whole other bunch of requirements.

In augment code (or any other IDE agent integration), I can just @powershell-advanced-function-design at the top so the agent references my rule file, and then I list requirements after.

Things like:

- Find any bugs or problems with this function and fix them.

- Optimize the function for performance and to reduce redundant operations.

- Add additional comments to the code in critical areas.

- Add debug and verbose output to the function.

- Add additional error handling to the function if necessary.

- Add additional validation to the function if necessary.

It was also essential for me to enable the "essential" MCP servers like sequential thinking, context7, fetch, filesystem, etc.

Powershell coding isn't particularly complex, so this might not work out exactly how you want if you're dealing with a larger codebase with very advanced logic.

Another tangent: Figma Make is actually extremely impressive. I tried it out yesterday to create a simple prompt manager application, and over a period of ~30min I had a working prototype with:

- An integrated markdown editor with HTML preview and syntax highlighting for code fences.

- A semi-polished UI with a nice category system for organizing prompts.

- All required modals / dialogs were automatically created and functioned properly.

I really think agentic coding DOES work. You just have to be very explicit with your instructions and planning.

YMMV.

Just for fun, I built a first person shooter game in UE5 from scratch using agentic coding. I've only spent a couple of months on it in my free time so far, and it isn't complete yet, but it's close enough that I could definitely release an early access version with another month or so of work. The most time consuming tasks have actually been tasks that agentic coding hasn't been able to help out with, like animations and mapping. The game is mostly written in C++ and sometimes the agent makes some bad decisions, but with a bit of extra guidance and being smart about my git commits so that I can revert and try again if necessary, I've always been able to make it work the way I want. I most definitely would not have been able to build this on my own in any reasonable amount of time.

FWIW it seems like it heavily depends on the agent + model you're using. I've had the most success with Claude Code (Sonnet), and only tried Opus 4.5 for more complex things. I've also tried Codex which didn't seem very good by comparison, plus a handful of other local models (Qwen3, GLM, Minimax, etc.) through OpenCode, Roo, and Cline that I'm able to run on my 128 GB M4 Max. The local ones can work for very simple agentic tasks, albeit quite slow.

> I suddenly have the homelab of my dreams, all the ideas previously in the "too long to execute" category now get vibe coded while watching TV or doing other stuff.

This is the true game changer.

I have a large-ish NAS that's not very well organised (I'm trying, it's a consolidated mess of different sources from two deacades - at least they're all in the same place now)

It was faster to ask Claude to write me a search database backend + frontend than try to click through the directories and wait for the slow SMB shares to update to find where that one file was I knew was in there.

Now I have a Go backend that crawls my NAS every night, indexes files to a FTS5 sqlite database with minimal metadata (size + mimetype + mtime/ctime) and a simple web frontend I can use to query the database

...actually I kinda want a cli search tool that uses the same schema. Brb.

Done.

AI might be a bubble etc. but I'll still have that search tool (and two dozen other utilities) in 5 years when Claude monthly subsciption is 2000€ and a right to harvest your organs on non-payment.