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

Why we built our own background agent

builders.ramp.com

Post reply on HN
Print view View original

11–20 of 29 posts

Re: Why we built our own background agent

#11

Post by llms01 »

ManuelKiessling wrote: post #8

I guess we all know and „love“ how every five minutes, some breathless hipster influencer posts „This changes everything!!!“ to every new x.y.1 AI bubble increment. But honestly? This here really is something. I can vividly imagine how in a not too far future, there will only be two types of product companies: those that work like this, and those that don’t — and vanish. Edit: To provide a less breathless take myself…

Yeah I feel somewhat the same way. This looks like some serious engineering effort went into it, and it looks like there should be a way to measure its impact on developer productivity and quality of output. I'm a bit hesitant considering finance is not an industry you want to introduce security problems in, but nonetheless will be a good test of these tools.

If it really does work I expect there will be many paid and open source variants that other companies can adopt into their workflows. So I'll patiently wait for the outcomes before trying something like this, but I'm glad someone is.

Re: Why we built our own background agent

#12

Post by cloudking »

We use https://devin.ai for this and it works very well. Devin has it's own virtual environment, IDE, terminal and browser. You can configure it to run your application and connect to whatever it needs. Devin can modify the app, test changes in the browser and send you a screen recording of the working feature with a PR.

Re: Why we built our own background agent

#13

Post by ColinEberhardt »

memset wrote: post #6

I work at Ramp and have always been on the “luddite” side of AI code tools. I use them but usually I’m not that impressed and a curmudgeon when I see folks ask Claude to debug something instead of just reading the code. I’m just an old(er) neckbeard at heart. But. This tool is scarily good. I’m seeing it “1-shot” features in a fairly sizable code base and fixes with better code and accuracy than me.

An important point here is that it isnt doing a 1-shot implementation, it is iteratively solving a problem over multiple iterations, with a closed feedback loop.

Create the right agentic feedback loop and a reasoning model can perform far better through iteration than its first 1-shot attempt.

This is very human. How much code can you reliable write without any feedback? Very little. We iterate, guided by feedback (compiler, linter, executing and exploring)

Re: Why we built our own background agent

#14

Post by martypitt »

cloudking wrote: post #12

We use https://devin.ai for this and it works very well. Devin has it's own virtual environment, IDE, terminal and browser. You can configure it to run your application and connect to whatever it needs. Devin can modify the app, test changes in the browser and send you a screen recording of the working feature with a PR.

Interestingly, Devin lists Ramp (the OP) as a customer on their front page.

Surprised they need both.

Re: Why we built our own background agent

#15

Post by martypitt »

This is a really great post - and what they've built here is very impressive.

I wonder if we're at the point where the cost of building and maintaining this yourselves (assisted with an AI Copilot) is now more effective than an off-the-shelf?

It feels like there's a LOT of moving parts here, but also it's deeply tailored to their own setup.

FWIW - I tried pointing Claude at the post and asking it to design an implementation, (like the post said to do) and it struggled - but perhaps I prompted it wrong.

Re: Why we built our own background agent

#17

Post by tosti »

Is overengineering the norm nowadays?

If you need a queue, lpd. If you need scheduling, cron. If you need backups, tar. If you need to communicate, email and irc. If you need to remote any of those, ssh.

Things shouldn't be difficult, yet they are.

Re: Why we built our own background agent

#18

Post by heffstaDug »

martypitt wrote: post #15

This is a really great post - and what they've built here is very impressive. I wonder if we're at the point where the cost of building and maintaining this yourselves (assisted with an AI Copilot) is now more effective than an off-the-shelf? It feels like there's a LOT of moving parts here, but also it's deeply tailored to their own setup. FWIW - I tried pointing Claude at the post and asking it to design an impleme…

I had this exact idea, I pointed Codex to it, with giving it context of our environment which is pretty complex. It is struggling, but that is because even our dev experience where I work is not great and not documented, so that would need to be lifted before I can reliably get an agent setup as well integrated as this blog post details.

Re: Why we built our own background agent

#19

Post by hrimfaxi »

tosti wrote: post #17

Is overengineering the norm nowadays? If you need a queue, lpd. If you need scheduling, cron. If you need backups, tar. If you need to communicate, email and irc. If you need to remote any of those, ssh. Things shouldn't be difficult, yet they are.

Do you have a specific critique or is this another dropbox-esque comment?

Re: Why we built our own background agent

#20

Post by tosti »

hrimfaxi wrote: post #19
tosti wrote: post #17

Is overengineering the norm nowadays? If you need a queue, lpd. If you need scheduling, cron. If you need backups, tar. If you need to communicate, email and irc. If you need to remote any of those, ssh. Things shouldn't be difficult, yet they are.

Do you have a specific critique or is this another dropbox-esque comment?

I tried reading TFA but it was full of garbage.
Post reply on HN