System Prompt: AI in the real world
System Prompt is a weekly podcast from DevMesh Services about what is actually happening in AI. How models work, where they fit in real businesses, and what changes when software starts reasoning.
Hosted by Val and Peter Green. Plain language. Real systems. No hype.
All episodes
September 9, 2026
The Reality of Physical AI w/ Hiten Sonpal
Physical AI gets a lot more serious when a bad answer can move thousands of pounds of machinery. In Episode 25 of System Prompt, Peter and Val sit down with Hiten Sonpal, CEO of RISE Robotics and a robotics veteran whose career spans iRobot, defense robotics, autonomous lawn care, Electric Sheep, and heavy industrial machinery.
September 3, 2026
NVIDIA, Asana, and New Models
NVIDIA agreeing to acquire Hugging Face changes more than who owns the biggest model repository in open-source AI. It may also make the open ecosystem harder to push around.
August 27, 2026
AI, Accountants, and the Future of the Profession
AI is not just changing the tools accountants use. It is changing the work itself.
August 19, 2026
Why China is winning the AI race (Qwen3.8:27B is amazing)
A 27 billion parameter model should not be competing with frontier AI.
August 13, 2026
Evals: How Do You Know Which AI Model to Trust?
The AI model at the top of a leaderboard may not be the best model for your system.
August 6, 2026
Conversation about Quantization(Also about hosting DeepSeekv4:Flash)
A 284-billion-parameter AI model should not fit on one local machine.
July 29, 2026
This Is Why Copilot Adoption Is Failing
AI agents do not earn trust because they work once.
July 15, 2026
Your Company Bought AI. Why Isn’t Anyone Using It?
Buying AI tools does not create adoption.
July 8, 2026
How AI is Transforming Food Discovery with Stupid Good AI
This week on System Prompt, we had David Leibner on to talk about StupidGood AI.
July 1, 2026
Enterprise AI Training Is Failing Because Tool Training Is Not Enough
Enterprise AI education is often reduced to showing employees how to use a chatbot or write better prompts.
June 25, 2026
What Fable 5’s Removal Reveals About AI Model Dependence
What happens when a model your workflow depends on is suddenly removed, restricted, or made more expensive?
June 17, 2026
AI Security Goes Beyond Prompt Injection
AI systems create attack surfaces that traditional application security does not fully cover.
June 12, 2026
Model Routing Is the Hidden System Behind Reliable AI Applications
Most AI applications are not powered by a single model handling every request the same way.
June 3, 2026
The AI Hardware Shift: When Local Inference Starts Making Business Sense
AI capability is not determined by models alone.
May 27, 2026
AI in Regulated Industries: Compliance, Liability, and Innovation with Joe Ewing
What changes when artificial intelligence enters an industry where mistakes can create legal, financial, or regulatory consequences?
May 20, 2026
AI-Native Products Still Need Traditional Software Engineering
What actually makes a product AI-native?
May 13, 2026
Before You Add AI, Make Sure It Solves the Right Business Problem
Businesses are being encouraged to add AI everywhere.
May 6, 2026
Everyone Says “Just Use RAG.” Here’s Why That’s Not Enough
Retrieval-Augmented Generation is often treated as the default answer whenever an AI system needs access to business data.
April 29, 2026
Are AI Models Getting Worse, or Are the Economics Catching Up?
AI models are improving on benchmarks, but many users still feel that the products are becoming less reliable.
April 22, 2026
AI Ethics Is Not Just About the Model, It Is About How We Use It
AI ethics is often discussed as if it begins and ends with the model.
April 15, 2026
Physical AI Is Coming, but It Still Struggles Outside Controlled Environments
Physical AI brings artificial intelligence out of software and into machines that can see, move, interact, and act in the real world.
April 8, 2026
AGENTIC CODING IS NOT A TOOL UPGRADE, IT CHANGES THE DEVELOPMENT WORKFLOW
Agentic coding is changing more than how quickly developers write code.
April 1, 2026
Are AI Agents Really Taking Jobs, or Changing the Work?
Are AI agents replacing workers, or are they changing the tasks and responsibilities inside existing jobs?
March 25, 2026
LOCAL VS. FRONTIER AI MODELS: WHAT SHOULD BUSINESSES ACTUALLY USE?
Businesses evaluating artificial intelligence are often pushed toward a false choice: use the most powerful frontier model available or run everything locally.
March 19, 2026
Will AI Agents Replace SaaS, or Change Who Builds Software?
AI agents are changing more than how businesses use software. They may also change where software gets built, who owns it, and what companies are willing to buy from traditional SaaS vendors.