Keri Miller

Revisiting this moment for Easter! ❤️

He Is Risen Indeed! Happy Easter to all who celebrate. May the hope of Christ’s resurrection fill your hearts with peace, joy, and renewal today and always.

OpenAI just released 11 free prompt courses. Beginner to advanced levels (I included all links): Use these courses to master ChatGPT prompts. [ bookmark 🔖 this thread for later ]

"I try not to #struggle against the #feelings of #hopelessness. They can follow me around in sulky silence like a fly at the border of my #brain ..I may be moving at a crawl, but I know that I must keep going, even if I think there’s no point": buff.ly/uaQmDdr #depression

The journey has led to this. The Chosen story continues Nov 15 @PrimeVideo

Lord Jesus, thank You for bearing our sins, for forgiving us in our weakness, and for finishing the work of redemption on the cross. Help us rest in Your sacrifice, receive Your grace, and walk in Your peace.

Take a moment… He knew what was coming, and Jesus still did it for you and me. John 15:13

Today I want to invite you to slow down, let this week become real to you… 

Let this verse be your guide today. Be still, and know that I am God. -Psalm 46:10

There are 3 ways you can use AI in your workflows. Non-Agentic (prompts), AI Agents and Agentic AI. Each works differently and has specific use cases. Here are the pros, cons and guidelines for using each. [ bookmark 🔖 this post for later ] 💻 Non-Agentic AI ↳ Simple prompt-response AI with no memory or reasoning. 🛠️ How it works: ↳ User enters one prompt, system replies in isolation ↳ Output generated instantly without refinement ↳ Interaction ends with no context retained 🟢 Pros: ↳ Fast, cheap, and widely accessible ↳ No technical setup required ↳ Ideal for one-off, simple tasks 🛑 Cons: ↳ No reasoning or memory ↳ Quality depends on prompts ↳ Weak for multi-step work 📈 How to start using: ↳ Open ChatGPT, Claude, or Gemini ↳ Write clear, specific prompts ↳ Copy, edit, and reuse output 🤖 AI Agent ↳ Single-task AI worker built to automate one job. 🛠️ How it works: ↳ User defines one clear role (e.g., update CRM) ↳ Agent pulls inputs and uses integrated tools ↳ Executes and outputs without supervision 🟢 Pros: ↳ Automates repetitive tasks ↳ Specialized and very capable ↳ Easy to refine within roles 🛑 Cons: ↳ Limited scope, rigid use ↳ Breaks if inputs are unclear ↳ Needs coordination to work with other agents 📈 How to start using: ↳ Select one repetitive task ↳ Connect LLM via Zapier, LangChain, or API ↳ Link inputs/outputs and test 🚀 Agentic AI ↳ Self-managing AI that plans, executes, and improves. 🛠️ How it works: ↳ Goal broken into smaller sub-tasks ↳ Connects to tools, APIs, and data sources ↳ Refines results with memory and feedback 🟢 Pros: ↳ Handles complex, multi-step projects ↳ Integrates with tools and databases ↳ Produces consistent outcomes 🛑 Cons: ↳ Slower and more expensive ↳ More complex and resource-intensive ↳ Difficult to configure, needs regular maintenance 📈 How to start using: ↳ Use LangChain, CrewAI, or AutoGen ↳ Assign roles (Planner, Executor, Critic) ↳ Add memory and feedback loops In short: Non-Agentic AI = prompts AI Agents = Automate one task Agentic AI = Run complex workflows Start with prompts. Then try AI Agents or Agentic AI. Use all three to get the most out of AI. 📌 Get Advanced ChatGPT Guide (free): bit.ly/3StIB3z 👉 Follow me @AndrewBolis for more and 🔄 Repost this to help others use AI

Sometimes the fastest way to type is to not type at all. Voice input. Now on desktop too!

Paris…are you ready? Register for pre-sale access by April 2 at CelineDion.com

One tiny candle illuminates a thousand. "A Great Awakening" is a new film coming to theaters nationwide April 3, telling the true story of George Whitefield and a spiritual movement that helped shape a nation at a critical moment in history. It’s a powerful reminder that the hope people were searching for then is the same hope we need today, found in Christ alone. Get your tickets now at hubs.la/Q048wCfP0

LinkedIn CEO: Young people 'can't afford to overlook' these 5 skills that AI can't replace cnbc.com/2026/03/31/ai-…

Lehigh County mourns Dan Wuchter, Sr., beloved Owner of Allentown Fairgrounds Farmers Market wfmz.com/news/area/lehi…

@AChVoice You’re welcome. 🙂

@KeriMillr thanks for resharing 🚏

“#Laughing is good for your health! Write down three things that never fail to make you #laugh.” — Get all the #mindfulness #journaling prompts in the post. The theme for April is "Imagination, #Creativity & Hope": buff.ly/MaMVLcJ #MondayBlogs #SelfLove #ChronicPain

Jordan McCullough takes us to a place words can’t reach! 🌈 #americanidol youtu.be/ilcR8pKmk9w?si…

Hannah Harper lifts hearts and souls with arms open wide! 💙 #americanidol youtu.be/yJ553LYYu1E?si…

Live streaming on LinkedIn is changing socialmediatoday.com/news/linkedin-…

🚨 This changes 3D creation more than people realize. Microsoft just quietly released an open-source model that turns a single image into production-ready 3D assets. It’s called TRELLIS.2 and it’s fast enough to feel unreal. Instead of relying on traditional mesh pipelines, it introduces something new: O-Voxel. A geometry format that skips the usual bottlenecks and converts into fully textured meshes in under 100ms using CUDA. That means: Real-time 3D generation is no longer theoretical. Here’s why this stands out: → No compromise between speed, quality, and clean topology → Handles complex structures natively with sparse voxel representation → Exports ready-to-use GLB assets with full PBR textures → Works directly with tools like Blender, Unity, and Unreal Engine → Fully open-source under MIT license with a pretrained 4B model available on Hugging Face → Includes a live web demo no setup required 4,600+ developers already starred it. We’re getting closer to a world where you can go from idea → image → 3D asset instantly. And when that happens, entire workflows in gaming, design, and content creation get rewritten.