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

We rewrote JSONata with AI in a day, saved $500k/year

reco.ai

Post reply on HN
Print view View original

101–110 of 278 posts

Re: We rewrote JSONata with AI in a day, saved $500k/year

#101

Post by leonidasv »

tabs_or_spaces wrote: post #95

The headline seems to be flashy indeed, but ai didn't really solve this imo. They just seemed to fix their technology choices and got the benefits. There's existing golang versions of jsonata, so this could have been achieved with those libraries too in theory. There's nothing written about why the existing libraries aren't good enough and why a new one needed to be written. Usually you need to do some due diligence…

> There's existing golang versions of jsonata, so this could have been achieved with those libraries too in theory

The only one I found (jsonata-go) is a port of JSONata 1.x, while the gnata library they've published is compatible with the 2.x syntax. Guess that's why.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#102

Post by leonidasv »

cjonas wrote: post #5

The docs indicate there are already 2 other go implementations. Why not just use one of those? https://docs.jsonata.org/overview.html

Those are compatible with the 1.x syntax while the gnata is compatible with the 2.x. Also, the repos haven't seen new commits in a long time.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#105

Post by heavyset_go »

leonidasv wrote: post #101
tabs_or_spaces wrote: post #95

The headline seems to be flashy indeed, but ai didn't really solve this imo. They just seemed to fix their technology choices and got the benefits. There's existing golang versions of jsonata, so this could have been achieved with those libraries too in theory. There's nothing written about why the existing libraries aren't good enough and why a new one needed to be written. Usually you need to do some due diligence…

> There's existing golang versions of jsonata, so this could have been achieved with those libraries too in theory The only one I found (jsonata-go) is a port of JSONata 1.x, while the gnata library they've published is compatible with the 2.x syntax. Guess that's why.

Looking at the releases, it looks like JSONata's 2.1.0 release from July 2025 added the `?:` and `??` syntax, and there hasn't been an update to the syntax since January 2020's 1.8.0 release that added `%`

Re: We rewrote JSONata with AI in a day, saved $500k/year

#106

Post by leonidasv »

Congrats to the team. Unfortunately many comments here are missing the big picture by attacking the previous architectural decisions with no context about why they were taken. It's always easy to say so in retrospect.

Also, I have to comment on the many commenters that spent time researching existing Go implementations just to question everything, because "AI bad". I don't know how much enterprise experience the average HN commenter these days have, but it's not usually easy to simply swap a library in a production system like that, especially when the replacement lib is outdated and unmaintened (which is the case here). I remember a couple of times I was tasked with migrating a core library in a production system only to see everything fall apart in unexpected ways the moment it touched real data. Anyway, the case here seems to be even simpler: the existing Go libs, apart from being unmaintened and obscure, don't support current feature of the JSONata 2.x, which gnata does. Period.

The article missed anticipating such critics and explaining this in more detail, so that's my feedback to the authors. But congrats anyway, this is one of the best use cases for current AI coding agents.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#107

Post by antonvs »

Aurornis wrote: post #19

The key point for me was not the rewrite in Go or even the use of AI, it was that they started with this architecture: > The reference implementation is JavaScript, whereas our pipeline is in Go. So for years we’ve been running a fleet of jsonata-js pods on Kubernetes - Node.js processes that our Go services call over RPC. That meant that for every event (and expression) we had to serialize, send over the network, ev…

Completely agree. We have > $50m from our most recent funding round, and even a cloud expense of $50k/year (in our case for storage) is considered a high priority to address. If it was $300k, our CTO would be running around with a butane torch setting everyone’s hair on fire until the problem was resolved.

But, venture funding does create a lot of weird inefficiencies which vary from company to company.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#108

Post by zer00eyz »

cromka wrote: post #67

If they were paying $500k/year, why haven't they paid someone to rewrite it? Surely would be cheaper still. But above everything else, this is a great example of how much JavaScript inefficiency actually costs us, as humanity. How many companies burn money through like this?

On top of that there are probably a few more hits for the containers, vm and hypervisor, all those pods have monitoring etc. All the layers of abstraction are just stacks of turtles giving the illusion of being easier but adding complexity and cost/overhead.

It is a security product, so unless they want to deal with the exfiltration charges on the data it's probably better to keep it in AWS. Thats the nasty double edge sword of "cloud", and how we're all getting locked in.

All the bits on their own seem to make perfect sense, but it's become apparent that the orchestra has been blind folded and given noise canceling head phones.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#110

Post by simultsop »

chii wrote: post #97
jdub wrote: post #91

> At Reco, we have a policy engine that evaluates JSONata expressions against every message in our data pipeline - billions of events, on thousands of distinct expressions. The original architecture choice and price almost gave me a brain aneurysm, but the "build it with AI" solution is also under-considered. This looks like a perfect candidate for existing, high quality, high performance, production grade solutions…

But if the ai built solution is slightly less stupid, then it's still a win isnt it?

but they saved $500k. Before some humans knew about constraints in it. Now nobody knows.

Jokes aside, we will probably see everyone doing this, trying to remove human hands off of code, because they corrupt and AI does not.

Joke jokes aside why did we even code until AI?

Post reply on HN