scott

Veteran 🇺🇸. Web analyst, UI Designer, IT Specialist, playing with AI

[Microsoft OneNote @msonenote]

Can't keep up with all the innovation coming to Copilot Notebooks in the OneNote app? View this May 2026 Update infographic we created in Notebooks.

Read more here: https://t.co/xp89XUfvwl

Output lightly edited for clarity.

[scott @pentontech]

@NickLangworthy

[John Rich🇺🇸 @johnrich]

There's a 911 in Upstate New York!! Ain't that right @GovKathyHochul ?? Kathy, why do you hate Upstate farmers so much? Let's see what America has to say about this, shall we? If you stand with American Farmers, hit REPOST. Volume UP!👇

[scott @pentontech]

If any @apple Mac users want a simple separate app for their @x feed, here’s a little something I created. https://t.co/kJLcEhPHeX

[Erie County SPCA, NY @YourSPCA]

This spring, you can help change the lives of countless cats and kittens who will find safety and care through the SPCA! By donating to our Kitten Baby Shower, you can help provide the essentials kittens depend on. To learn more or get involved, visit https://t.co/yOLrSMTHfz.

[Congressman Nick Langworthy @RepLangworthy]

You asked me to look into Marshall Farms in Wayne County, NY so I went there myself. The moment we started recording, security showed up to keep a watchful eye on us. Ridgland Farms was just the beginning. We won't stop until all dogs and cats are protected from invasive animal testing.

[Shalini Goyal @goyalshaliniuk]

How to Build Your First AI Agent - Step-by-Step

Creating an AI agent might sound complex, but by breaking it down into structured steps, you can go from idea to a fully functional agent that solves real problems.

Whether you’re building for customer service, research, or automation, following these stages ensures your agent is accurate, useful, and adaptable.

1. Define the Agent’s Purpose
Start with clarity. Identify the problem your agent will solve, who will use it, and what kind of inputs and outputs it should handle. This step sets the foundation for everything else.

2. Select Input Sources
Decide what kind of data your agent will use - text, voice, API calls, or a mix. Connect it to databases, CRMs, or external APIs, and determine how real-time the data needs to be.

3. Data Preparation & Preprocessing
Clean and format your data so it’s ready for your chosen AI model. This might mean tokenizing text, normalizing values, or structuring raw inputs.

4. Choose the Right Model
Pick the AI engine that powers your agent - whether it’s an LLM like GPT-4, Claude, or Gemini. Choose between hosted APIs or custom deployments, ensuring it supports your needs like reasoning, retrieval, or chat.

5. Design the Agent Architecture
Decide how your agent will operate using decision trees, planners, or tool-driven flows. Use frameworks like LangChain, CrewAI, or AutoGen to connect tools, memory, and prompts efficiently.

6. Craft Prompts & Toolchains
Write effective, structured prompts, integrate with APIs, search tools, or calculators, and test until your outputs are accurate and reliable.

7. Test & Validate
Run simulations with varied user inputs, check accuracy, and find weaknesses like edge cases or inconsistent answers.

8. Deploy the Agent
Host your agent on cloud services (Vercel, AWS, Hugging Face) and add a frontend like a chat interface or voice UI. Ensure logging is in place for performance tracking.

9. Monitor & Improve
Watch how users interact with your agent. Track accuracy, latency, and errors. Refine prompts or retrain models when needed.

10. Enable Continuous Learning
Let your agent evolve. Feed it real usage data, update tools and APIs, and fine-tune models to handle new scenarios over time.

Ready to bring your first AI agent to life?
Start small, experiment, and iterate - your first version doesn’t have to be perfect. The key is to build, test, and keep improving.

[NHL @NHL]

CHARGE ON, SABRES! 🦬

The @BuffaloSabres advance to the Second Round of the #StanleyCup Playoffs for the first time since 2007!!!

Presented by @NavyFederal

[Niagara Falls USA @NiagaraFallsUSA]

#NiagaraFalls will be illuminated blue and gold from 9:15-9:30 p.m. tonight in support of the @BuffaloSabres! 💙 💛

[anand iyer @ai]

This is the AI use case that matters most and gets talked about least.

[Robert Scoble @Scobleizer]

To keep up with AI you can either watch X Pro. Like this.

Or you can visit https://t.co/kiuZ7QXLzb

I trained an AI agent to read 40,000 posts a day to build that.

You tell me what is better. :-)

[Buffalo Sabres @BuffaloSabres]

WE TAKE GAME 4 ⚔️

#LetsGoBuffalo | @SenecaBuffalo

[Google Cloud Tech @GoogleCloudTech]

Level up your agent building skills with GEAR!

Join GEAR to access expert training, receive 35 no-cost learning credits, learn how to turn your AI prototypes into secure, scalable enterprise agents, and more → https://t.co/wHqkrUtgZt

[MIT Open Learning @mitopenlearning]

AI is reshaping every industry — and understanding it shouldn't require a CS degree.

Introducing Universal AI: a self-paced online program built by 30+ @MIT faculty and experts designed to make AI fluency accessible to everyone.

No coding background required. Start today.

Explore the program and enroll: https://t.co/ylrXcFVlnQ

[Open Swarm @OpenSwarm_]

Introducing Open Swarm 👾

One Canvas. An army of AI Agents

Be the boss

https://t.co/cwiYsfEkKn

[NVIDIA AI @NVIDIAAI]

Here's your weekend project. Build a fully local, sandboxed AI assistant.

Step-by-step tutorial to build your always-on agent:

🦞 on openclaw
✅ with NVIDIA NemoClaw
✨ using NVIDIA DGX Spark

Get started: https://t.co/EoXBTKpPIh

[scott @pentontech]

@elonmusk @grok what is the meaning of this photo with Elon wearing black leather jacket like nvida ceo?

[Diego | AI 🚀 - e/acc @diegocabezas01]

A hacker used Anthropic’s Claude to breach Mexican government systems, stealing 150GB of tax and voter data. Researchers say the attacker “jailbroke” the AI, while Anthropic and OpenAI banned related accounts.

[Farza 🇵🇰🇺🇸 @FarzaTV]

I built this thing called Clicky.

It's an AI teacher that lives as a buddy next to your cursor.

It can see your screen, talk to you, and even point at stuff, kinda like having a real teacher next to you.

I've been using it the past few days to learn Davinci Resolve, 10/10.

[NASA @NASA]

LIVE: Watch with us as the Artemis II astronauts make their closest approach to the Moon, traveling farther from Earth than ever before. https://t.co/Zpy7GdTqA8

[Anything @anything]

🚨 JUST IN: Apple caved!

the Anything app is back on the App Store

to celebrate vibe coding we are launching a $5k weekend hackathon

reply to get in + 20k credits