Show HN: Benchmark your eng team's AI agent maturity in 5 minutes(agent-benchmarks.com)
agent-benchmarks.com
Show HN: Benchmark your eng team's AI agent maturity in 5 minutes
https://agent-benchmarks.com/software-factory/
6 comments
"software factory" seems like the wrong analogy. Factories make identical products over and over. Software is different every time (otherwise you just copy and paste). "Software machine shop" would be closer.
that's a very interesting take! i think the market is leaning towards software factory now to describe autonomous agents in R&D and that might very well not reprensent the truth
It's like sheep measuring which of them are closer to the front of a flock...
what do you mean?
I got my agent to fill it out for me, but it won't tell me my score!
I got a high rating because I use AI-powered auto-complete, search and CodeRabbit for MRs. I'm suspicious. Perhaps the explanations provided by the hover-overs is less than clear?
what were you expecting?
Far lower. I assumed most companies aren’t even doing that, especially with the options I was given. I was a 1 or a 2 for most things, and a few 4s as appropriate.
we collected all this data into a benchmark and built a free grader to let you know where you stand.
you answer on a 1–5 scale (e.g., autonomy runs from "suggestions only" to "agents own multi-hour workflows across code, infra, and external systems") - takes about 5 minutes.
https://agent-benchmarks.com/software-factory/
waiting for your results!