Why we built our own background agent

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.

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.

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.

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.

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.

Probably the best internal ai platform I've seen to date, incredible work.

Fun marketing experiment, but you basically implemented ralph wiggum in the cloud.

Claude code locally in a vm and/or with work trees will 1 shot far better without burning cloud infra cash.

I’d bet this ends up wasting more money and time than it’s worth in practice.

And here I am trying to get 1 terminal agent to control 4-5 other terminal agents

Reading this article and discovering how Ramp team use Modal for sandboxed dev environment just saved us weeks of custom infra development and potentially months of headache, thanks you !

The commitment to reducing friction is really incredible. Are they implying that any developer could recreate the system with AI from the description?

Definitely impressive. How many engineering hours did you need to build an MVP?

i wonder what percentage of PRs etc is now from non eng?

the chrome extension bit is super interesting and well thought out

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“.

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.