Super excited to speak at the @LangChain conf in exactly two weeks! 🚀
I'll be taking the stage to talk about our Deepagent and how we're pushing the boundaries of what autonomous systems can actually do in production. If you're building next-gen agents, come say hi! 👇
🗓️ @mondaydotcom is scheduled for Interrupt.
Monday Sidekick is an AI assistant that can execute work, manage tasks, and conduct research autonomously. At Interrupt, the Agent Conference by LangChain, Head of AI @bruchim will take us behind the scenes.
We’ll learn how Deep Agents runs in the background to execute complex, multi-step tasks for users, taking us through the tool loading, middleware pipeline, delegation-first architecture, memory, and optimizations for resilience.
Catch @bruchim's talk along with all the others at Interrupt on May 13-14 in San Francisco.
Get tickets here 👉 https://t.co/YIb9u5fiGR
.@mondaydotcom had one agent trying to handle 200+ tools.
Context pollution everywhere.
The LLM was confused, costs rising, and it still wasn't working.
@omribruchim on rebuilding Sidekick with Deep Agents: https://t.co/fS6u3D1X6V
monday Sidekick turns a board into a shareable, interactive visual.
A deck, a report, or a full page you click through, all built from your data that's already there.
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: https://t.co/bwn0sximKZ
Uhhh… your memory is failing, my friend. And this was sent after the dinner, not before. Have the receipts. I don’t begrudge you in any way, but let’s be truthful.
🏃♂️ I've gamified my own run so I can race my own ghost with the Meta Ray-Ban Display.
I built a web app for the glasses, loaded a previous GPX from Strava, and dropped game mechanics on top.
Pick up coins when you keep pace, sprint zones reward extra points if you push, and a mini leaderboard on the lens shows how you're tracking against your past self in real time.
Best part: it actually works. Seeing your ghost 20 m ahead is a way stronger nudge than any number on a watch. 😅
Today, we're launching shift. We're starting by cleaning your apartment in New York City, for free.
Here's how it works. Book a shift cleaning. A vetted shift operator comes to your home wearing one of our devices. They clean. They leave. You pay nothing.
In exchange, we record the cleaning. Robotics is being built on data about how people do daily tasks, and the value of that recording is what funds the service. Anything personal in it is anonymized before the recording is processed.
By now, you have heard about the shift to AI more times than you can count. About the shift toward you, the part where you actually feel it, you have heard almost nothing. Shift is what starts to make it concrete, in specific cities, with specific services.
Today, cleaning in New York. Soon, handymen, repairs, and errands across the globe. And this is just one side of shift, with more on the way.
Comment “shift” and we’ll send you an early access link.
30 seconds of a monday agent being your teammate:
Assign it, it reads the thread, it gets things DONE.
That's it. Just your new teammate, doing teammate things.
I’m here! @LangChain#interrupt
Nothing beats meeting people in person.
If you’re around, come say hi, especially if you want to talk about the future of us as human beings in an agents-first world 👀
Every once in a while, the way we work actually changes.
Not just a new tool, a REAL shift.
Last year, I joined https://t.co/BGxo5Mstsu to help lead the platform behind one of the biggest transformations the company has made in recent months.
Today https://t.co/BGxo5Mstsu makes its biggest move yet - from managing work to actually getting it done. People and agents, working together, on one platform.
This is what work looks like from here.
Couldn't feel prouder to be at a company helping define what comes next!
Congrats! Today, your team gets stronger, faster, bigger, and better.
Reintroducing https://t.co/SQQj2vlQRM - the AI work platform where people and agents work together as one team.
You set the goals, and your agents get the work DONE: research, tickets, reports, follow-ups, budget tracking, and so (so, so) much more.
✅ Easy to build
✅ Always on
✅ Fully under your control
And we're just getting started. Over the coming weeks, we'll walk you through new ideas on how to leverage agents in your work, build-along sessions, and handy tips from our agents experts.
Big day for us, finally sharing what we’ve been cooking for a while.
Over the past year, we kept seeing the same pattern:
AI agents look great in demos, until real users break them.
Today, we’re fixing that with 𝘃𝗶𝗯𝗲-𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴
to build real-time, tailored evals and guardrails
for your agents, in minutes.
Define your intent with a prompt or a few examples.
We generate edge-case datasets,
and train a model aligned to your use case,
outperforming state-of-the-art LLMs at a fraction of the cost.
(Research paper with benchmarks in the comments)
If you’re building AI agents, don’t let your users be the ones who discover the failures. Be the one who makes AI agents reliable in production and takes control at scale.
Start vibe-training for free: https://t.co/H9b3aZleNN
Today, we’re launching @Globster_ai: 1-click AI agents powered by @nvidia NemoClaw and running on our https://t.co/SQQj2vlQRM managed cloud.
👉 It works where you work — WhatsApp, Telegram, and more.
👉 It remembers context — and gets sharper every time you use it.
👉 And it works for you and never stops!
Start your 7-day free trial at https://t.co/v6laQKwmAU
Home Launch introduces:
MUXI the application server for AI agents.
Deploy your entire multi agent system as a single, coherent intelligence with one command.
https://t.co/Wp3n9RCUY6
Websites have web servers.
APIs have application servers.
AI agents never had their own layer.
Until now.
MUXI is the application server for AI agents. Define agents, memory, tools, and orchestration in a single file MUXI runs it.
Multi tenant access control.
Observability. Orchestration.
Built in.
Your users interact with one consistent AI powered by a coordinated system of specialized agents behind the scenes.
Your users get Jarvis.
You get infrastructure that actually works in production.
No frameworks to stitch together.
No infrastructure to rebuild.
Just declare and deploy.
https://t.co/Wp3n9RCUY6
⸻
**This post is sponsored by @homelaunch
HomeLaunch is an amplifier for early stage startups, a network where entrepreneurs back each other through distribution, reach, and momentum. Instead of building in isolation, founders leverage a shared surface area to get their products in front of the right audiences, faster.
Join us and be part of the movement.**