Super Prompt: Building in the Era of AI Agents

AI Agents at Work: Scaffold Required Dec 03, 2025

We review four clips from the Dwarkesh Patel Podcast with Satya Nadella, Microsoft's CEO. I highly recommend Dwarkesh’s show—technical & nerdy, but excellent.

Satya talks about scaffolding—the software wrapped around AI models to make them actually work.

So we speak with someone building that scaffolding: Neil McKechnie runs two AI-first startups as a CTO.

He discusses how he orchestrates up to twelve different language models—GPT-5, Claude, Gemini, Llama, Mistral, Cohere, Perplexity.

We discuss what it actually takes to build production systems with LLMs today—and what that reveals about the agent future we’re being pitched.

Dwarkesh's Podcast:

https://www.youtube.com/@DwarkeshPatel

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Whose Agent Is It Anyways? Nov 07, 2025

Description:

AI agents from OpenAI, Google, and Anthropic promise to act on your behalf—booking flights, handling tasks, making decisions. What kind of agency do these systems actually have? And whose interests are they serving?

Enterprise AI agents are already deployed in customer support, code generation, and task automation. Consumer agents—ChatGPT Agent Mode, personal task assistants—face a wider gap between marketing promises and actual capabilities.

The alignment problem: agents need access to your calendar, email, and personal preferences to help you effectively. But the agent that knows you well enough to serve you is also positioned to steer you. When you delegate decisions to an agent, who decides what success looks like?

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

AI Safety: Constitutional AI vs Human Feedback Jun 17, 2024

With great power comes great responsibility. How do leading AI companies implement safety and ethics as language models scale? OpenAI uses Model Spec combined with RLHF (Reinforcement Learning from Human Feedback). Anthropic uses Constitutional AI. The technical approaches to maximizing usefulness while minimizing harm. Solo episode on AI alignment.
REFERENCE

OpenAI Model Spec

https://cdn.openai.com/spec/model-spec-2024-05-08.html#overview

Anthropic Constitutional AI

https://www.anthropic.com/news/claudes-constitution

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Open Source LLMs: How Open Is "Open"? Jun 10, 2024

Notable open source large language models from Meta, French AI company Mistral (valued at $2B), Microsoft, and Apple. Not all open source models are equally open—the restrictions and licensing constraints you need to know before deploying one. Solo episode.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Open Source AI: The Safety Debate Jun 03, 2024

Why enterprises and entrepreneurs choose open source LLMs like Meta's Llama—cost-effectiveness, control, privacy, and security. The safety and ethics debate: which poses greater risk to humanity, open source or proprietary AI models? Both? Neither? Solo episode on open source LLMs.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

LLM Benchmarks: How to Know Which AI Is Better May 27, 2024

Beyond ChatGPT and Gemini: Anthropic's Claude and the $4 billion Amazon investment. How AI industry benchmarks work, including LMSYS Arena Elo and MMLU (Measuring Massive Multitask Language Understanding). How benchmarks are constructed, what they measure, and how to use them to evaluate LLMs. Solo episode.

Anthropic's Claude
https://claude.ai [Note: I am not sponsored by Anthropic]
LMSYS Leaderboard
https://chat.lmsys.org/?leaderboard

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Multimodal AI: When ChatGPT Learned to See May 20, 2024

Recent updates from Google and OpenAI feature multimodal capabilities—AI that processes multiple input types simultaneously. Why multimodal models outperform single-modality systems, demonstrated through a hypothetical chatCAT that helps owners understand their cats. Solo episode on multimodal architecture.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Google Gemini: Three Models, One Strategy May 13, 2024

Google's Gemini family of multimodal AI models compared to OpenAI equivalents. What Nano, Pro, and Ultra each do, how they compare to GPT-3.5, GPT-4, and ChatGPT, and what "multimodal" means in practice. Solo episode on Google's LLM strategy.

https://gemini.google.com. (Note: I am not sponsored by Google.)

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Building Custom GPTs: Seven Lessons from GPT Builder Dec 15, 2023

Creating a travel planning AI using OpenAI's GPT Builder with no code. Seven takeaways from building a custom GPT, what the process reveals about prompt engineering, and the constraints of the no-code approach. Includes demonstration of the Holiday travel GPT. Solo episode.

You'll need to be Open AI Plus subscriber to access this GPT. (Note: I am not sponsored by Open AI.)
https://chatgpt.com/g/g-FURrBQAh8-holiday

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Enterprise LLMs: Cloud Deployment Strategy Nov 06, 2023

Deploying large language models for enterprise applications. Rackspace CTO Jeff DeVerter discusses implementing Google PaLM for sales, enabling Azure and AWS customers, and why your LLM choice should probably match your cloud provider. Private cloud deployment for data confidentiality and thinking in data pipelines from the start. Featuring Jeff DeVerter, Rackspace Technology.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

ChatGPT in the Classroom: Yale's Response Oct 23, 2023

How is generative AI changing teaching, learning, and evaluation? Yale's Assistant Dean of Academic Affairs Alfred Guy discusses the university's AI guidance and its implications for education. What educators are grappling with, and how institutions are adapting. Featuring Alfred Guy, Yale College.

Yale's AI guidance is published online here:
https://poorvucenter.yale.edu/AIguidance

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

AI Screenwriting: GPT-4 Meets the Writers Strike Aug 14, 2023

Creating a science fiction blockbuster pitch using ChatGPT power prompts: Role Play, Chain of Thought, and Self Critique. How these techniques improve output, and the AI-related issues at stake in the 2023 Writers and Actors Strike. Solo episode on generative AI and creative work.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

ChatGPT Guardrails: The One Question It Won't Debate Jul 24, 2023

Ask ChatGPT if it possesses human-like intelligence and you'll get a definitive "NO"—unusual for a system that typically provides balanced perspectives. This guardrail reveals the ethical concerns OpenAI built into the system. What those concerns are, and whether Isaac Asimov's 80-year-old Robot Laws still apply. Solo episode.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

ChatGPT vs The Onion: Can AI Get the Joke? Jul 08, 2023

Does ChatGPT have a sense of humor? We test whether it would find an Onion headline funny: "Microsoft renames ChatGPT to ClippyChat." Large language models are better at analyzing humor than creating it—here's why. Solo episode exploring AI and comedy.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

ChatGPT Jailbreaks: The Grandma Exploit Jul 03, 2023

How do you extract prohibited information from ChatGPT? Grandma and DAN exploits trick language models into violating their own policies. Why these techniques work, what they reveal about LLM architecture, and how companies protect against prompt injection attacks. Solo episode on LLM security.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

AI Hallucinations: Bug or Feature? Jun 19, 2023

What are AI hallucinations, and should we consider them bugs or features? The top 10 categories of AI hallucinations with examples, how ChatGPT might hallucinate an answer about Blade Runner, and ChatGPT debating itself on whether hallucinations help or harm humanity. Solo episode.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

LLM Training: Superman's Kryptonite-Proof Suit May 29, 2023

Why isn't Superman's suit Kryptonite-proof? This question reveals how large language models are trained. We break down transformers (the T in GPT), self-attention mechanisms, and the inference process—using Superman to explain why GPT-3 can generate coherent answers to questions it's never seen before. Solo episode on LLM architecture.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Large Language Models: Getting from GPT-3 to chatGPT May 15, 2023

How do ChatGPT, GPT-3, and Large Language Models relate to each other? We explore the hierarchy: artificial intelligence, neural networks, large language models, GPT-3, and ChatGPT. What each term means, how they connect, and why the order matters. Solo episode for AI newcomers.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

What Is ChatGPT? Explained May 08, 2023

How would you describe ChatGPT in your own words? This solo episode provides definition and context for newcomers to AI. I answer the question myself, then ask ChatGPT to evaluate my answer. Introduction to what ChatGPT is, how it works, and where it fits in the AI landscape.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

DALL-E: Why AI Can't Make Your Perfect Pizza Mar 24, 2023

Why is it so hard to get DALL-E to create the exact image you envision? PhD candidate and entrepreneur Arijit Ray discusses generative AI constraints, and his startup training AI to predict social media responses and run marketing focus groups. From scientist to entrepreneur. Featuring Arijit Ray, Boston University.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Voice AI: Your Phone Knows You're Sick Feb 20, 2023

AI that screens for diseases like COVID-19 based on voice patterns. Speaking a simple phrase into your phone, the system analyzes your voice profile for respiratory illness, and can be trained for conditions ranging from obesity to substance use. How voice biomarkers work and what this means for health screening. Featuring Mario Arancibia, CTO and entrepreneur.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

AI Art Authentication: Faking a $450M Leonardo Feb 13, 2023

Can neural networks authenticate artwork? Husband-and-wife team Steven and Andrea Frank developed AI to assess painting authenticity. They tested it on Salvator Mundi, which sold for $450 million as a Leonardo da Vinci—the most expensive painting ever sold. How the technology works and what it found. Featuring Maroof Farooq, AI Engineer at Nvidia.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

AlphaGo vs Lee Sedol: The Move That Shocked Humanity Feb 06, 2023

AlphaGo, created by DeepMind, played 9-dan champion Lee Sedol in a televised match that reportedly changed how China's leadership viewed AI. The game of Go has more board positions than atoms in the observable universe. How AlphaGo approached this complexity, and what the unexpected moves revealed about machine learning. Featuring Maroof Farooq, AI Engineer at Nvidia.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Self-Driving AI: Training in The Matrix Jan 30, 2023

A digital replica of the driving environment is being built for autonomous vehicle training. The goal: make simulation indistinguishable from reality for self-driving AI. How this works, why it matters, and what happens when virtual training meets real-world edge cases. Featuring Maroof Farooq, AI Engineer at Nvidia.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Self-Driving AI: The Bicycle Problem Jan 23, 2023

What's easy for a teenage driver but hard for autonomous vehicles? Bicycles, bike racks, motorcycles—edge cases that reveal the gap between current AI capabilities and the roads we actually drive on. Tesla and other companies pitch fully autonomous vehicles as safer roads. We examine whether that claim holds up against the technical reality of perception systems trying to navigate human complexity. Featuring Maroof Farooq, AI Engineer at Nvidia.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Self-Driving Cars: Why Tesla and Waymo Disagree Jan 16, 2023

Tesla and Waymo take fundamentally different approaches to self-driving. We examine the technical differences, autonomous driving levels 1-5, and why stop signs remain one of the hardest problems to solve. Featuring Maroof Farooq, AI Engineer at Nvidia.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Facial Recognition: How to Disappear with Makeup Jan 09, 2023

How facial recognition works for surveillance—and how to fool it. We cover adversarial techniques using physical objects: clothing, accessories, even makeup. The technical principles behind why these methods work, and what they reveal about computer vision vulnerabilities. Featuring Maroof Farooq, AI Engineer at Nvidia.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

ChatGPT Explained: Before ChatGPT Existed Jan 02, 2023

What makes GPT-3 different from previous language models? Recorded before ChatGPT's launch, this episode breaks down Generative Pre-trained Transformers—what those words actually mean, supervised vs unsupervised learning, and how these models generate text. Featuring Maroof Farooq, AI Engineer at Nvidia.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Hot Dog. Not Hot Dog: Building Image Recognition AI Dec 26, 2022

How do you build AI that recognizes hot dogs? We walk through image classification from the ground up using the Seefood app from HBO's Silicon Valley. Learn about dataset acquisition, training methodology, and why scaling from hot dogs to all foods is harder than it sounds. Featuring Maroof Farooq, AI Engineer at Nvidia.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Welcome to Super Prompt! Dec 19, 2022

Tony Wan, the host of Super Prompt, describes his vision for the podcast, who it's for, who he is, and why he’s doing it.

To stay in touch, sign up for our newsletter at https://www.superprompt.fm

Our TOPPODCAST Picks

Follow Us

Stay Connected

Super Prompt: Building in the Era of AI Agents

Related Podcasts

Links

Stay Connected