Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Agentic AI Handbook: Production-Ready Patterns

nibzard.com

Post reply on HN
Print view View original

121–130 of 151 posts

Re: The Agentic AI Handbook: Production-Ready Patterns

#121

Post by torben-friis »

alkonaut wrote: post #95
torben-friis wrote: post #60

Earlier quoted context omitted.

I’m not particularly proAI but I struggle with the mentality some engineers seem to apply to trying. If you read someone say “I don’t know what’s the big deal with vim, I ran it and pressed some keys and it didn’t write text at all” they’d be mocked for it. But with these tools there seems to be an attitude of “if I don’t get results straight away it’s bad”. Why the difference?

I don't understand how to get even bad results. Or any results at all. I'm at a level where I'm going "This can't just be me not having read the manual". I get the same change applied multiple times, the agent having some absurd method of applying changes that conflict with what I say it like some git merge from hell and so on. I can't get it to understand even the simplest of contexts etc. It's not really that the c…

>I don't understand how to get even bad results. Or any results at all. I'm at a level where I'm going "This can't just be me not having read the manual".

>I get the same change applied multiple times, the agent having some absurd method of applying changes that conflict with what I say it like some git merge from hell and so on. I can't get it to understand even the simplest of contexts etc.

That is weird. results have a ton of variation, but not that much.

Say you get a claude subscription, point it to a relatively self contained file in your project, hand it the command to run relevant tests, and tell it to find quick win refactoring opportunities, making sure that the business outcome of the tests is maintained even if mocks need to change.

You should get relevant suggestions for refactoring, you should be able to have the changes applied reasonably, you should have the tests passing after some iterations of running and fixing by itself. At most you might need to check that it doesn't cheat by getting a false positive in a test or something similar.

Is such an exercise not working for you? I'm genuinely curious.

Re: The Agentic AI Handbook: Production-Ready Patterns

#122

Post by TeMPOraL »

cobolexpert wrote: post #37
hahahahhaah wrote: post #21

Earlier quoted context omitted.

I feel like just use claude code. That is it. Use it you get the feel for it. Everyone is over complicating. It is like learning to code itself. You need flight hours.

This is something that continues to surprise me. LLMs are extremely flexible and already come prepackaged with a lot of "knowledge", you don't need to dump hundreds of lines of text to explain to it what good software development practices are. I suspect these frameworks/patterns just fill up the context with unecessary junk.

There's no such thing as universal "good software development practices". There's only lots of opinions. Some are more popular, some less; some are language, domain or company-specific (or even tool-specific - see various webshit frameworks whose idiosyncrasies spill over to significantly alter coding style), and many exist only as historical baggage - but they all largely conflict with each other. And LLMs have seen them all.

Consider as an example, that "Clean Code" used to be gospel, now it's mostly considered a book of antipatterns, and many developers prefer to follow Ousterhout instead of Uncle Bob. LLMs "read" both Clean Code and A Philosophy of Software Design, but without prompting they won't know which way you prefer things, so they'll synthesize something more-less in between these two near-complete opposites, mostly depending on the language they're writing code in.

The way I think about it is: "You are a staff software engineer with 15 years of experience in " is doing 80% of the job, by pulling in specific regions in the latent space associated with good software engineering. But the more particular you are about style, or the more your project deviates from what's the most popular practice across any dimension (whether code style or folder naming scheme or whatnot), the more you need to describe those deviations in your prompt - otherwise you'll be fighting the model. And then, it's helpful to describe any project-specific knowledge such as which tools you're using (VCS, testing framework, etc.), where the files are located, etc. so the model doesn't have to waste tokens discovering it on its own.

Prompts are about latent space management. You need to strengthen associations you want, and suppress the ones you don't. It can get wordy at times, for the same reason explaining some complex thought to another person often takes a lot of words. First sentence may do 90% of the job, but the remaining 20 sentences are needed to narrow down on a specific idea.

Re: The Agentic AI Handbook: Production-Ready Patterns

#123

Post by prettygood »

embedding-shape wrote: post #43
prettygood wrote: post #40

Earlier quoted context omitted.

I'm so happy someone else says this, because I'm doing exactly the same. I tried to use agent mode in vs code and the output was still bad. You read simple things like: "We use it to write tests". I gave it a very simple repository, said to write tests, and the result wasn't usable at all. Really wonder if I'm doing it wrong.

You didn't actually just say "write tests" though right? What was the actual prompt you used? I feel like that matters more than the tooling at this point. I can't really understand letting LLMs decide what to test or not, they seem to completely miss the boat when it comes to testing. Half of them are useless because they duplicate what they test, and the other half doesn't test what they should be testing. So many…

No, that was an exaggeration. The prompt was decent. I explained the point of the repository, that I wanted full coverage with tests, that it could keep going until it worked. Maybe that was still not enough. With how others talk about it, I must be missing something.

Re: The Agentic AI Handbook: Production-Ready Patterns

#124

Post by embedding-shape »

prettygood wrote: post #123
embedding-shape wrote: post #43

Earlier quoted context omitted.

You didn't actually just say "write tests" though right? What was the actual prompt you used? I feel like that matters more than the tooling at this point. I can't really understand letting LLMs decide what to test or not, they seem to completely miss the boat when it comes to testing. Half of them are useless because they duplicate what they test, and the other half doesn't test what they should be testing. So many…

No, that was an exaggeration. The prompt was decent. I explained the point of the repository, that I wanted full coverage with tests, that it could keep going until it worked. Maybe that was still not enough. With how others talk about it, I must be missing something.

For tests, you need to be precise about what it should test, how it should test it, and what the assertions should be, otherwise you'll mostly get trash, they're exceptionally horrible at writing tests. Which makes sense, most programmers are too, but given the importance of correct tests, it's probably the part that needs to most human handholding right now.

Re: The Agentic AI Handbook: Production-Ready Patterns

#125

Post by embedding-shape »

Balinares wrote: post #116
embedding-shape wrote: post #43

Earlier quoted context omitted.

You didn't actually just say "write tests" though right? What was the actual prompt you used? I feel like that matters more than the tooling at this point. I can't really understand letting LLMs decide what to test or not, they seem to completely miss the boat when it comes to testing. Half of them are useless because they duplicate what they test, and the other half doesn't test what they should be testing. So many…

There are a lot of comments on HN and other places breathlessly gushing about agents totally doing everything end to end, so I couldn't blame someone new to this space for naively assuming that agents would be able to handle a well-bounded problem such as test coverage reasonably well.

> naively assuming that agents would be able to handle a well-bounded problem such as test coverage reasonably well.

We haven't figured out a way for humans to do that well :P I still see people arguing about "80% test coverage is obviously better than 70%" and similar dumb sentiments that completely misses the point.

But agree with the first part, LLMs are massively oversold and it's hard to blame users for believing them. Tempered expectations as always win.

Re: The Agentic AI Handbook: Production-Ready Patterns

#126

Post by cobolexpert »

TeMPOraL wrote: post #122
cobolexpert wrote: post #37

Earlier quoted context omitted.

This is something that continues to surprise me. LLMs are extremely flexible and already come prepackaged with a lot of "knowledge", you don't need to dump hundreds of lines of text to explain to it what good software development practices are. I suspect these frameworks/patterns just fill up the context with unecessary junk.

There's no such thing as universal "good software development practices". There's only lots of opinions. Some are more popular, some less; some are language, domain or company-specific (or even tool-specific - see various webshit frameworks whose idiosyncrasies spill over to significantly alter coding style), and many exist only as historical baggage - but they all largely conflict with each other. And LLMs have seen…

Maybe my initial message was overly harsh, I mostly agree with your points here. I think maybe the point of disagreement is exactly _how much_ extra prompt is necessary to approach 100% of the job, but this is quite hard to measure (obviously). Your point about latent space management is a good mental model to have IMO.

Re: The Agentic AI Handbook: Production-Ready Patterns

#127

Post by JeremyNT »

ramraj07 wrote: post #68
alkonaut wrote: post #20

All of this might as well be greek to me. I use ChatGPT and copy paste code snippets. Which was bleeding edge a year or two ago, and now it feels like banging rocks together when reading these types of articles. I never had any luck integrating agents, MCP, using tools etc. Like if I'm not ready to jump on some AI-spiced up special IDE, am I then going to just be left banging rocks together? It feels like some of the…

I recently pasted an error I found into claude code and asked who broke this. It found the commit and also found that someone else had fixed it in their branch. You should use claude code.

If your org has a relationship with MS/OpenAI (many do!) you can also use OpenCode with GPT-5.2 for some pretty impressive results.

Once you see what is currently possible with this technique you will understand that programming as a field is doomed, or at the very least it's becoming something almost unrecognizable.

Re: The Agentic AI Handbook: Production-Ready Patterns

#128

Post by JeremyNT »

alkonaut wrote: post #100
photios wrote: post #56

Earlier quoted context omitted.

Copilot's agent mode is a disaster. Use better tools: try Claude Code or OpenCode (my favorite). It's a new ecosystem with its own (atrocious!) jargon that you need to learn. The good news is that it's not hard to do so. It's not as complex or revolutionary as everyone makes it look like. Everything boils down to techniques and frameworks of collecting context/prompt before handing it over to the model.

Sadly we have some partnership meaning it's Copilot or nothing.

If you can use the Copilot CLI, it's highly likely you can use OpenCode with the same API key. It's worth doing a little research.

The CLI tool matters. If you're not using opencode/claude you're missing out. But the latest OpenAI models are really quite good.

Re: The Agentic AI Handbook: Production-Ready Patterns

#129

Post by Nekobai »

galaxyLogic wrote: post #70
torben-friis wrote: post #60

Earlier quoted context omitted.

I’m not particularly proAI but I struggle with the mentality some engineers seem to apply to trying. If you read someone say “I don’t know what’s the big deal with vim, I ran it and pressed some keys and it didn’t write text at all” they’d be mocked for it. But with these tools there seems to be an attitude of “if I don’t get results straight away it’s bad”. Why the difference?

Well one could say that since it's AI, AI should be able to tell us what we're doing wrong. No? AI is supposed to make our work easier.

Certainly, every tool is supposed to make our work easier or more productive, but that doesn't mean that every tool is intuitive or easy to learn to use effectively or even to use it at all.

Re: The Agentic AI Handbook: Production-Ready Patterns

#130

Post by vivzkestrel »

kstenerud wrote: post #109

It's unbelievable how productive AI has made me. With the release of the latest Claude, I'm now able to achieve 100x more than I could have without it. In one week, I fine-tuned https://github.com/kstenerud/bonjson/ for maximum decoding efficiency and: * Had Claude do a go version ( https://github.com/kstenerud/go-bonjson ), which outperforms the JSON codec. * Had Claude do a Rust version ( https://github.com/kstener…

thats all? I made an emulator for every single console in the planet called Universal Emulator in one week, I have not published it because that would be illegal /s
Post reply on HN