Comment by tobyhinloopen | Hacker News Reader

Comment by tobyhinloopen | Hacker News Reader

Parent Full thread

Many of my prompts include _somewhat_ sensitive details because they're tailor-made for each project. This is a more generic prompt I've been using for my code generation tool:

https://gist.github.com/tobyhinloopen/e567d551c9f30390b23a0a...

More about this prompt:

https://bonaroo.nl/2025/05/20/enforced-ai-test-driven-develo...

Lately, I've been letting the agent write the prompt by ordering it to "update the prompt document with my expressed preferences and code conventions", manually reviewing the doc. Literally while writing this comment, I'm waiting for the agent to do:

> note any findings about this project and my expressed preferences and write them to a new prompt document in doc, named 20250610-<summary>.md

I keep a folder of prompt documents because there's so many of them (over 30 as of writing this comment, for a single project). I have more generic ones and more specific ones, and I usually either tell the agent to find relevant prompt documents or tell the agent to read the relevant ones.

Usually over 100K tokens is spent on reading the prompts & documentation before performing any task.

Here's a snippet of the prompt doc it just generated:

https://gist.github.com/tobyhinloopen/c059067037a6edb19065cd...

I'm experimenting a lot with prompts, I have yet to learn what works and what doesn't, but one thing is sure: A good prompt makes a huge difference. It's the difference between constantly babysitting and instructing the agent and telling it to do something and waiting for it to complete.

I had many MRs merged with little to no post-prompt guidance. Just fire and forget, commit, read the results, manually test it, and submit as MR. While the code is usually somewhere between "acceptable" and "obviously AI written", it usually works just fine.

I guess it is tool-dependent, but do you pass in that enormous prompt on each request?

Yes, I inject multiple documents like that before every session. The documents I inject are relevant to the upcoming task.

The one I shared is a variant of the “Base” document, I have specific documents per use case. If I know I’m adding features (controller actions), I inject a prompt containing documentation how to add routes, controllers, controller actions, views, etc and how to format views, what helpers are commonly used.

If I’m working on APIs, I have API specific prompts. If I’m working on syncs with specific external services, I have prompts containing the details about these services.

Basically I consider every session a conversation with a new employee. I give them a single task and include all the relevant documentation and guidelines and wish them good luck.

Sometimes it takes a while, but I generally have a second issue to work on, in parallel. So while one agent is fixing one issue, I prepare the other agent to work on the second. Very occasionally I have 3 sessions running at the same time.

I barely write code anymore. I think I’ve not written a single line of code in the last few work days. Almost everything I submit is written by AI, and every time I have to guide the LLM and I expect the mistake to be repeated, I expand the relevant prompt document.

Last few days I also had the LLM update the prompt documents for me since they’re getting pretty big.

I do thoroughly review the code. The generated code is different from how I would write it, sometimes worse but sometimes better.

I also let it write tests, obviously, and I have a few paragraphs to write happy flow tests and “bad flow” tests.

I feel like I’m just scratching the surface of the possibilities. Im writing my own tools to further automate the process, including being able to generate code directly on production and have different versions of modules running based on the current user, so I can test new versions and deploy them instantly to a select group of users. This is just a wild fantasy I have and I’m sure I will find out why it’s a terrible idea, but it doesn’t stop me from trying.

Thanks!

Sorry to belabor the question, when you say "before every session", how many "things" do you do in a session? You say you give them a single task, but do you end up chatting back and forth with the agent in that session? I guess I'm unsure how far back the "context" goes in a conversation and if would drift from your directives if the conversation went back and forth too much.

One task per session, sometimes split into multiple smaller tasks in the same session if they’re closely related.

Usually it’s like “implement a worker/class/module for x” (which will act as a model) and when it did that successfully (with tests and such) I commit everything and I continue the session building the GUI, since the GUI requires deep knowledge of the thing it just made.

If I tell it to make the GUI and worker at the same time, it will usually be poorly written with logic in the views rather than in a model, and it will be tested through views while I want dedicated tests for the model

Ok, that makes sense. But when you continue the session building the GUI, do you run into it making mistakes because it doesn't have the earlier stuff (ie, your original directions) still in its context?

Sometimes but usually not anymore. Highly depends on the model, Claude Sonnet 3.7 has been the most reliable, but each model has its own quirks

Reply on news.ycombinator.com