In financial services, the ability to explain how a conclusion was reached matters as much as the conclusion itself. This agent uses LangSmith to preserve that decision log: every query issued, every response received, and every intermediate result produced before the final
AUTOMATION
-
Rippling AI shipped millions using Deep Agents and LangSmith in 6 months
By
–
.
@Rippling AI runs on Deep Agents and LangSmith. Here’s how they shipped to millions of users in 6 months. -
Benedict Evans dismisses AI exposure predictions as nonsense
By
–
.@benedictevans: "People try to predict a profession is X or Y% exposed to AI—this is just the most ridiculous bunch of deluded horsesh*t." https://t.co/Nsra5jHNUg pic.twitter.com/U1Ok1E5Y9h
— Lenny Rachitsky (@lennysan) 1 juin 2026.
@benedictevans
: "People try to predict a profession is X or Y% exposed to AI—this is just the most ridiculous bunch of deluded horsesh*t." -
Composer 2.5 now available in Grok Build, excels at complex tasks
By
–
Composer 2.5 is now available inside Grok Build.
— xAI (@xai) 1 juin 2026
Composer 2.5 is a fast, highly intelligent model that excels on long-running tasks and following complex instructions. pic.twitter.com/x7k4zVuVdWComposer 2.5 is now available inside Grok Build. Composer 2.5 is a fast, highly intelligent model that excels on long-running tasks and following complex instructions.
-
Search as Code replaces tool-calling with async search primitives
By
–
The traditional tool-calling approach suffers from high latency, manual control flow, and context pollution. With Search as Code, the model composes search primitives: fanning out queries asynchronously, deduping, filtering, joining, and ranking before results hits its context.
-
Fleet APAC agents gain new computer use capability
By
–
Fleet APAC agents just unlocked a new major capability: computer use!
-
DellTechWorld 2026: H2O.ai CEO and Dell CTO discuss AI scaling, governance, cost
By
–
At #DellTechWorld 2026, http://
H2O.ai Founder & CEO @srisatish joined @DellTech
' CTO Satish Iyer and @theCUBEto discuss what it takes to operationalize AI at scale — from infrastructure and governance to cost control, sovereignty, and real-world business outcomes. -
Codex working nonstop since 11am, feels like an AI employee
By
–
I launched Codex on a goal at 11am, it's 5pm and it's still working. I've never felt so strongly the feeling of having an AI working for me. Like, it's doing a normal workday right now. I'm working on something else while it…
-
Agents initiate purchase orders for out-of-stock parts with organizational approval.
By
–
If parts aren't in stock, the agent can initiate purchase orders where organizations approve that autonomy level.
-
XR headsets, AI agents, and the future of 3D collaboration with AutoCAD, Maya, Blender.
By
–
Honestly if we put this demo in a fancy XR headset, we’d call it jarvis. The future of 3d doesn’t involve the death of autocad, maya and blender. It turns those tools into a shared canvas of collaboration with ai agents. https://t.co/VwxOpFBZvH
— Bilawal Sidhu (@bilawalsidhu) 1 juin 2026Honestly if we put this demo in a fancy XR headset, we’d call it jarvis. The future of 3d doesn’t involve the death of autocad, maya and blender. It turns those tools into a shared canvas of collaboration with ai agents.