Agents aren't mature yet
The technology you want to use looks right for the problem but is not yet mature, and someone has to decide.
Where it goes wrong
The cost of a technical decision lands on the people who implement and maintain it. Usually that is not the person who made it. On technical merit alone the decision looks right, but the bill goes to someone who had no say.
So "we can make it work" is the wrong test. I have won that argument and shipped the thing, and I was still wrong. Getting a tool to do what you want is not the same as your team being able and willing to own it.
How I'd handle it
Before we compare options, I ask who will maintain this once it ships, and whether that person is in the room. A team that will have to run something fragile has a valid engineering reason to object, and this outranks a benchmark.
Then I compare the options against what that team can support today. The right decision is the one the team is ready to live with.
Where I've done this
I chose Rust at Redis while its async support was still unfinished, for a daemon that failover depends on. It ran on nightly builds and the libraries kept changing under me. The pieces I needed went stable months later, but the daemon held up well in production.
SunbitAt Sunbit I got an immature Kafka Streams to do what we needed. The backend team would have had to run it, and one of their engineers told me, in effect, that he would not maintain code he could not understand. He was right.
Recognize this on your team?
