Pinned Tweet
I’ve been working on a thing. For a while. I’m very, very excited about it. Come check out Great Expectations!
Abe Gong retweeted
Today we're launching Mastra Factory.
When we started building a factory, we weren't sure what to expect.
But over the last few weeks it's has been writing 30% of our PRs, closing 60% of issues.
Factory is free + open-source, now you can try it too:
producthunt.com/products/mas…
Abe Gong retweeted
We're excited to introduce Claude Code, Cursor, and Codex agents in Mastra.
Starting today, Mastra is now a meta-harness:
Abe Gong retweeted
we raised a $13m seed round from 120+ of Silicon Valley’s top investors
for @mastra, the leading TypeScript agent framework
Congrats, @TMobile , after 5+ hours of customer support calls, you have unbroken the cell line that you broke on our first call.
The second line still doesn't work, though.
Hey, @OptimizerAI, I paid for a subscription, but my account is still stuck on Free Tier settings. Only 100 credits; can't download SFX.
What gives?
I'm kinda disappointed every time I get to the end of the month and haven't maxed out my Windsurf credits.
Abe Gong retweeted
For the past six months, I haven't checked email directly, but rather have relied on an AI email assistant to triage and draft emails for me
This is an example of an "ambient agent"
We're open sourcing the code today, as well as a hosted version for people to try out
👇
Erasing/synthesizing category distinctions is one of the hardest conceptual moves you can make, especially in a large organization.
Founder mode question: what's the difference between having taste (in the Steve Jobs/Apple sense of "taste") and micromanaging?
Abe Gong retweeted
I then asked it to spell Arrington Capital correctly and got this. I love AI so much.
Definitely worth a read, whether you agree or not
This essay by Ted Chiang is really good and makes many points I agree with.
newyorker.com/culture/the-we…
Note that it is possible to say this while also thinking that LLMs and diffusion models are amazing technical breakthroughs that will (eventually) revolutionize society. It's about seeing the technology for what it is, and finding the right use cases. Right now, it feels like we're at a stage similar to when people tried to sell personal computers in the early 1980s with the argument that they could help you organize your recipe collection.
Paging @TerribleMaps , even though this is, in fact, an awesome map.














