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

Building an AI agent inside a 7-year-old Rails monolith

catalinionescu.dev

Post reply on HN
Print view View original

31–40 of 59 posts

Re: Building an AI agent inside a 7-year-old Rails monolith

#31

Post by hombre_fatal »

only-one1701 wrote: post #22
Tiberium wrote: post #21

Earlier quoted context omitted.

I get that the water stereotype is funny, but it gets tiring after a while (because it's not actually true).

For what it’s worth: yes, it’s not technically true, but the reason it’s sticking around is because it conveys a deeply felt (and actually true) sentiment that many many people have: the output of generative AI isn’t worth the input.

Well, it more demonstrates that people will quickly latch on to convenient lies that support what they want to be true, yet impede real discussion of the trade offs if they can’t even get the basic facts right.

It’s not a good thing.

Re: Building an AI agent inside a 7-year-old Rails monolith

#32

Post by nbaugh1 »

shevy-java wrote: post #23

"I was at SF Ruby, in San Francisco, a few weeks ago. Most of the tracks were, of course, heavily focused on AI" It may be the current "Zeitgeist", but I find the addiction to AI annoying. I am not denying that there are use cases to be had that can be net-positive, but there are also numerous bad examples of AI use. And these, IMO, are more prevalent than the positive ones overall.

And yet, you clicked the link

Re: Building an AI agent inside a 7-year-old Rails monolith

#33

Post by Kerrick »

zhisme wrote: post #30
mark_l_watson wrote: post #26

I really enjoyed reading the code listings in the article. Many years ago I was a Ruby fanatic, even wrote a book on Ruby, but for work requirements I was pulled to Java and Python (and occasionally Clojure and Common Lisp). I liked how well designed the monolith application seems to be from the brief description in the article. Coincidentally I installed Ruby, first time in years, last week and spent a half hour exp…

Could you share the book name? Sounds interesting!

Based on their username, I would guess it's Ruby Quickly: Ruby and Rails for the Real World (ISBN 978-1932394740, Manning, 2006).

Re: Building an AI agent inside a 7-year-old Rails monolith

#34

Post by galdauts »

midnightclubbed wrote: post #9

What does the end user do with the AI chat? It sounds like they can just use it to do searches of client information… which the existing site would already do.

You see, now they can market the tool as AI-powered! I‘m sure the sales department is overjoyed.

Re: Building an AI agent inside a 7-year-old Rails monolith

#35

Post by kubb »

rahimnathwani wrote: post #12

The article is dated December 2025, but: I checked a few OpenAI models for this implementation: gpt-5, gpt-4o, gpt4. Seems like a weird list. None of these are current generation models and none are on the Pareto frontier.

But they precede the knowledge cutoff.

Re: Building an AI agent inside a 7-year-old Rails monolith

#36

Post by simonw »

only-one1701 wrote: post #22
Tiberium wrote: post #21

Earlier quoted context omitted.

I get that the water stereotype is funny, but it gets tiring after a while (because it's not actually true).

For what it’s worth: yes, it’s not technically true, but the reason it’s sticking around is because it conveys a deeply felt (and actually true) sentiment that many many people have: the output of generative AI isn’t worth the input.

Urgh, I know that it's a solid explanation but I hate the "it may not be true but it captures a truth that people feel" argument so much!

See also "instagram is spying on you through your microphone". It's not, but I've seen people argue that it's OK for people to believe that because it supports their general (accurate) sentiment that targeted ads are creepy.

Re: Building an AI agent inside a 7-year-old Rails monolith

#37

Post by rahimnathwani »

kubb wrote: post #35
rahimnathwani wrote: post #12

The article is dated December 2025, but: I checked a few OpenAI models for this implementation: gpt-5, gpt-4o, gpt4. Seems like a weird list. None of these are current generation models and none are on the Pareto frontier.

But they precede the knowledge cutoff.

You mean you suspect the article itself was written by AI?

Re: Building an AI agent inside a 7-year-old Rails monolith

#38

Post by simonw »

aidos wrote: post #15
pell wrote: post #3

Was there any concern about giving the LLM access to this return data? Reading your article I wondered if there could be an approach that limits the LLM to running the function calls without ever seeing the output itself fully, e.g., only seeing the start of a JSON string with a status like “success” or “not found”. But I guess it would be complicated to have a continuous conversation that way.

> No model should ever know Jon Snow’s phone number from a SaaS service, but this approach allows this sort of retrieval. This reads to me like they think that the response from the tool doesn’t go back to the LLM. I’ve not worked with tools but my understanding is that they’re a way to allow the LLM to request additional data from the client. Once the client executes the requested function, that response data then g…

I was confused by that too. I think I've figured it out.

They're saying that a public LLM won't know the email address of Jon Snow, but they still want to be able to answer questions about their private SaaS data which DOES know that.

Then they describe building a typical tool-based LLM system where the model can run searches against private data and round-trip the results through the model to generate chat responses.

They're relying on the AI labs to keep their promises about not training in data from paying API customers. I think that's a safe bet, personally.

Re: Building an AI agent inside a 7-year-old Rails monolith

#39

Post by simonw »

tovej wrote: post #25
bitmasher9 wrote: post #17

Earlier quoted context omitted.

By interact directly with the API, are you having the user to make curl calls to your backend? We build front ends for the API to make our applications easier to use. This is just another type of front end.

No, obviously not. I mean having a regular web frontend with a fuzzy search form.

That's effectively what they built. The LLM is an implementation detail for how they got a version of fuzzy search to work.

Re: Building an AI agent inside a 7-year-old Rails monolith

#40

Post by simonw »

rahimnathwani wrote: post #12

The article is dated December 2025, but: I checked a few OpenAI models for this implementation: gpt-5, gpt-4o, gpt4. Seems like a weird list. None of these are current generation models and none are on the Pareto frontier.

I was surprised they settled on GPT-4o for performance reasons. I'd expect GPT-5-mini to be as fast and better.
Post reply on HN