Prachi M
108 posts
Prachi M
@PrachiM05
Weaver of the Kool-Aid Matrix at @bentolabsai
somewhere Katılım Haziran 2025
31 Takip Edilen9 Takipçiler
Prachi M retweetledi
Teams running agents in production, what is one thing you wish your monitoring could tell you that it currently cannot?
English
Prachi M retweetledi
Why agents that work in staging often degrade in production?
It's usually a diagnostic failure. Users use your agents in ways you can't even imagine, that results in failures that are even harder to catch and work on.
Our framework helps you spot which layer is actually breaking.
Read here 👇🏻
bentolabs.ai/blog/nature-vs…
English
Tired: another billboard almost no one will pay attention to. and even if they do, how will you attribute campaign success?
Wired: @UseCorgi Cafe Drink sponsorship where nearly every patron is your ICP holding your brand logo in their hands like a walking billboard for a fraction of the cost.
English
@brookeleblanc @UseCorgi Do you have maybe any kind of plan for more enterprise friendly brands?
English
Prachi M retweetledi
We ran our recursive learning layer on Terminal-Bench 2.0. Same agent. Same model. Same harness. Same budget.
The result: Claude Sonnet went from 42.2% → 52.4%. A +10.2 percentage-point lift, significant at p < 0.05, with a 13:3 task-level win/loss ratio (internal).
The only variable was a learning layer.
We wrote a full technical breakdown on what changed, why it worked, and what this means for production AI agents.
Read it here 👇
bentolabs.ai/blog/tb2-recur…
English
Genuine question for @Premium and @XBusiness
Has support gotten slower lately?
I've raised multiple tickets over time, including one while trying to purchase Gold, and never heard back. I have another open request now and still haven't received a response.
English
English
.@BentoLabsAI is the monitoring and learning layer for long-running agents. Their learning layer gives agents model-jump gains: Sonnet 4.5 went 42.2%→52.4% on TB2 (Internal).
Congrats on the launch, @Abhinavv_soni & @kacppian!
ycombinator.com/launches/Qcw-b…
English
Finallyyyy!!!! From scrolling through others’ launch videos to seeing ours, what a day!
Y Combinator@ycombinator
.@BentoLabsAI is the monitoring and learning layer for long-running agents. Their learning layer gives agents model-jump gains: Sonnet 4.5 went 42.2%→52.4% on TB2 (Internal). Congrats on the launch, @Abhinavv_soni & @kacppian! ycombinator.com/launches/Qcw-b…
English
Prachi M retweetledi
My advice to founders in 2026: spend tokens, not headcount.
Record everything. Make your company queryable. Build self-improving loops.
Before long, AI won’t just help you operate your company. It will make it self improving.
Don't think AI adoption, think AI transformation.
This is the biggest shift in how startups get built since cloud computing.
English
Prachi M retweetledi
Prachi M retweetledi
Consider this a glimpse of what's coming
#launchsoon
Abhinav Soni@Abhinavv_soni
Almost didn't document the day, my team made sure we did. Some days you just feel the shift. We booked a studio, brought in a team, and spent the day trying to capture what @BentoLabsAI actually is right now. Where we started, where we are, and where we're going. It's one thing to build in silence. It's another to finally show it in a much bigger way. We've been deep in production agent systems, working with some of the top teams running AI at scale today. The problem we set out to solve is more real than ever. Not ready to say more just yet. But it's close. Stay tuned.
English
Prachi M retweetledi
My co-founder @Abhinavv_soni clearly does not like being kept away from his agents.
PS: BTS of the BTS.
#launchsoon
English
Prachi M retweetledi
Almost didn't document the day, my team made sure we did.
Some days you just feel the shift. We booked a studio, brought in a team, and spent the day trying to capture what @BentoLabsAI actually is right now. Where we started, where we are, and where we're going. It's one thing to build in silence. It's another to finally show it in a much bigger way.
We've been deep in production agent systems, working with some of the top teams running AI at scale today. The problem we set out to solve is more real than ever.
Not ready to say more just yet. But it's close. Stay tuned.
English
Prachi M retweetledi
@BentoLabsAI (YC P26) is now live on the YC Directory.
YC has been one of the most intense environments we’ve ever experienced. Every week forces you to build faster, think sharper, and execute better.
We’ve gone from building for leading AI teams to seeing them start using BentoLabs.
More soon.
Check us out here👇🏻
ycombinator.com/companies/bent…
English
We're live on the YC Directory.
Check us out here👇🏻
ycombinator.com/companies/bent…
Andd stay tuned. More coming soon!!
BentoLabs AI (YC P26)@BentoLabsAI
We are live on the YC Directory. ycombinator.com/companies/bent…
English