Introduction
Introduction Statistics Contact Development Disclaimer Help
[HN Gopher] Why we built our own background agent
___________________________________________________________________
Why we built our own background agent
Author : jrsj
Score : 104 points
Date : 2026-01-12 15:36 UTC (1 days ago)
web link (builders.ramp.com)
w3m dump (builders.ramp.com)
| sdwr wrote:
| The commitment to reducing friction is really incredible. Are
| they implying that any developer could recreate the system with
| AI from the description?
| inssein wrote:
| Probably the best internal ai platform I've seen to date,
| incredible work.
| ostegm wrote:
| This is a great writeup! Could you share more about the sandbox
| <-> client communication architecture? e.g., is the agent
| emitting events to a queue/topic, writing artifacts to object
| storage, and the client subscribes; or is it more direct
| (websocket/gRPC) from the sandbox? I've mostly leaned on
| sandbox.exec() patterns in Modal, and I'm curious what you found
| works best at scale.
| memset wrote:
| 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.
| keyle wrote:
| This basically sums up where we're at. Undeniably useful but
| careful in approach.
| ColinEberhardt wrote:
| 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)
| ManuelKiessling wrote:
| 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:
|
| What I can very realistically imagine is that just like today
| sane and level-headed startups go ,,let's first set up some
| decent infrastructure-as-code, a continuous delivery pipeline,
| and a solid testing framework, and then start building the
| product for good", in the future sane and level-headed startups
| will go ,,let's first set up some decent infrastructure-as-code,
| a continuous delivery pipeline, a solid testing framework, and a
| Ramp-style background agent -- and then start building the
| product for good".
| 383toast wrote:
| the chrome extension bit is super interesting and well thought
| out
| 383toast wrote:
| i wonder what percentage of PRs etc is now from non eng?
| cloudking wrote:
| 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.
| martypitt wrote:
| Interestingly, Devin lists Ramp (the OP) as a customer on their
| front page.
|
| Surprised they need both.
| martypitt wrote:
| 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.
| heffstaDug wrote:
| 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.
| theturtletalks wrote:
| And here I am trying to get 1 terminal agent to control 4-5 other
| terminal agents
| tosti wrote:
| 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.
| hrimfaxi wrote:
| Do you have a specific critique or is this another dropbox-
| esque comment?
| tosti wrote:
| I tried reading TFA but it was full of garbage.
| falloutx wrote:
| This kind of project totally shows that Claude Code is nothing
| special, if anything it lacks a lot of features. I hope every
| company develops a model agnostic coding agent rather than using
| a one tightly controlled by one company.
___________________________________________________________________
(page generated 2026-01-14 13:01 UTC)
You are viewing proxied material from hngopher.com. The copyright of proxied material belongs to its original authors. Any comments or complaints in relation to proxied material should be directed to the original authors of the content concerned. Please see the disclaimer for more details.