Reminds me of the GDM robots! I'm super excited about getting to play with one soon!

https://www.techeblog.com/google-deepmind-ai-mini-humanoid-r...

I think engineers would be better at sales if they were better customers.

Congrats on launching! Curious how early the Mastra team thinks people should be thinking about evals and setting up a pipeline for them.

We tend to recommend folks spend a few hours writing evals after they spend a couple weeks prototyping. Then they get a sense of how valuable evals are for their use-case.

We think about evals a bit like perf monitoring -- it's good to have RUM but also good to have some synthetic stuff in your CI. So if you do find them valuable, useful to do both.

I could see another tier that comes with 1,0000-10,000 included requests included at 1/10 of the cost being a good idea. Might be really hard for a small startup to support those customers out the gate though!

Less aggressively, pricing is a historically bad way to create urgency in software

This post is a right of passage

I think if EVERY tool you use at work is in the Office suite, teams is just better. If you have any other tools like one off SaaS or devTools, Muddy could be a fit.

I fear you're right. As a remote worker, I feel that more touchpoints and areas of collaboration can really nurture a better culture. Muddy feels like a good step in that direction. While my day-to-day experience with Office365 isn't horrible, it's this kind of innovation that I want to support.

Curious what you had in mind?

Team is a handful, fluctuated over the years but never more than 8.

We’ve always treated everything we do as an experiment. We’re not trying to keep anything alive for the sake of it.

thanks, good job, respect the hustle.

I think we might have more base interfaces (notes, sheets) but we want to encourage people to keep building first class software. All in one is worst of all