Lmst

AI tools are everywhere. But which ones actually do the work for you? This post breaks it down.

@sumisu3 @sphcow Bingo! And speaking to the analogy with Liberty Alliance... Eve Maler just posted about the topic of standardizing delegated authority across the Agentic AI models!

https:/workshop.vennfactory.com/p/3-identity-links-the-d-word

#agenticai #identity #standards #synergy

🚀 71% of devs made the switch to Agentic AI in just 30 days — but why? 🤔 From 10x productivity boosts to AI agents acting like digital CEOs, find out how workflows are quietly transforming before your eyes! 🔍✨
#AgenticAI #Automation #FutureOfWork
👉
https://medium.com/@rogt.x1997/71-of-developers-switched-to-agentic-ai-what-happened-in-just-30-days-bf6e3267519b

7 trends shaping digital transformation in 2025 - and AI looms large. From autonomous enterprises built on a hybrid workforce to a house of AI agents, here's where digital transformation goes next.
https://zurl.co/0cIBJ
#ai #agenticai #digitaltransformation

@sphcow In case you haven't seen it, Google published what appears to be a reasonable comparison (or rationale?) of A2A vs MCP:

https://a2aprotocol.ai/docs/guide/a2a-vs-mcp

... though it's about the protocols, and not the standards process itself. I'd be keen to see what you come up with in an open process review of both. :)

#agenticai #a2a #mcp

@sphcow In response to your Call to Action... sign me up. I've been similarly diving deep into MCP and came to the same conclusions. There's a lot to discuss, and I'm happy to join (or convene) a call with folks interested in discussing how to help develop the projects as a true "open standard."

BTW - Google's A2A protocol falls into a similar state.

#agenticai #opensource #standards

People are raving about how the next big thing is "Agentic AI”.

I'm pretty sure I don’t want that…

#AgenticAI #Matrix

Agent Smith from The Matrix inside an industrial looking building. A green tint is prominent in the whole frame.

So it seems #agenticAI is just using the LLM to generate a workflow in which LLMs may or may not be called again. Didn't realize AI could develop a #lisp.

What if AI didn’t just summarize your notes, but scheduled the meeting, assigned the tasks, and followed up without you? That’s Agentic AI.

Read more 👉 https://lttr.ai/AfY3R

#AgenticAI #AI #OpenAI

🔥 AI’s future isn’t bigger models — it’s smarter connections! Discover how distributed systems thinking is saving agentic AI from collapse. 🧠🌐
#AIInfrastructure #TechFuture #AgenticAI
https://medium.com/@rogt.x1997/what-happens-when-ai-agents-forget-inside-the-crisis-nobody-talks-about-6ee61e43bef5

RPA was the starting point. Intelligent automation is the evolution. But now we’re stepping into agentic AI—where digital workers make autonomous decisions.
At @Nexbotix we’re building flows where agents manage exceptions, chase missing documents, and even coordinate with humans where needed.
Automation isn’t about scripts—it’s about smart decision-making at scale.
#Automation #AgenticAI #NexBotix #DigitalTransformation #AI

"Building on the recent empirical work of Kwa et al. (2025), I show that within their suite of research-engineering tasks the performance of AI agents on longer-duration tasks can be explained by an extremely simple mathematical model — a constant rate of failing during each minute a human would take to do the task. This implies an exponentially declining success rate with the length of the task and that each agent could be characterised by its own half-life. This empirical regularity allows us to estimate the success rate for an agent at different task lengths. And the fact that this model is a good fit for the data is suggestive of the underlying causes of failure on longer tasks — that they involve increasingly large sets of subtasks where failing any one fails the task. Whether this model applies more generally on other suites of tasks is unknown and an important subject for further work."

#AI #GenerativeAI #AIAgents #AgenticAI https://www.tobyord.com/writing/half-life

This isn’t ChatGPT. This is AI that makes decisions and takes action. Agentic AI is the next leap in productivity.

Read more 👉 https://lttr.ai/AfWIW

#AgenticAI #AI #OpenAI

How Agentic AI can Boost Productivity in the Modern Workplace: https://lttr.ai/AfU7V

#AgenticAI #AI #OpenAI

Weeknotes for 2025, week 24: https://denisdefreyne.com/weeknotes/2025-w24/

#Weeknotes #AgenticAI #AppKit #indiedev

I shared a post on the OpenAI forum about using Pomerium to secure remote MCP servers with Zero Trust. It’s all open source. We show how to expose MCP servers (like GitHub or Notion) to LLM clients without leaking tokens or re-implementing OAuth.

Happy to chat more over a coffee chat or podcast!

https://community.openai.com/t/zero-trust-architecture-for-mcp-servers-using-pomerium/1288157 #ztna #security #mcp #agenticai

"As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent’s resilience on natural language inputs — an especially dangerous threat when agents are granted tool access or handle sensitive information. In this work, we propose a set of principled design patterns for building AI agents with provable resistance to prompt injection. We systematically analyze these patterns, discuss their trade-offs in terms of utility and security, and illustrate their real-world applicability through a series of case studies."

https://arxiv.org/html/2506.08837v2

#AI #GenerativeAI #LLMs #PromptInjection #AIAgents #AgenticAI #CyberSecurity