Your AI Gets It Wrong Because You're Talking to It Like a Human
Clarity for non-technical founders → https://techforfounder.com/ (My main hub. Practical insights, no overwhelm.) Schuyler Dragoo, Chief Strategy Officer at Kiingo AI on Tech for Founder Podcast with Panida Wayrojpitak, explains why AI is easy to use but hard to use well, and why generic prompts produce generic outputs. Drawing on experiences using ChatGPT as a tool to understand social situations and an art practice of observing and mimicking Boston geese, Schuyler emphasizes that AI misreads users due to incomplete context windows, unstated assumptions, overloaded prompts, and undefined terms. They describe context engineering, structured workflows, documentation, and tools like MCP servers to guide models more precisely. Practical advice includes experimenting to learn a model’s assumptions, iterating based on outputs, building a prompt library, using a role-task-output-context prompt formula, defining good vs. bad responses, providing scenarios and examples, treating AI like an intern who needs onboarding, and starting with low-stakes, repetitive workflows such as email and question-generation. 00:00 Why AI Misreads You 00:37 AI Insight 01:43 Context and Assumptions 02:24 Fixing Misinterpretations 03:54 Observing Geese 05:45 Play to Learn Tools 06:19 Intention vs Perception 07:51 Prompt Formula That Works 09:11 What to Automate 11:56 Building Translation Systems 12:52 Treating AI Like an Intern 15:48 First Simple Workflow 17:30 Examples Beat Perfect Clarity 19:33 Wrap Up and Resources More about Schuyler Dragoo: Linkedin: / schuyler-dragoo-mfa-a99672333 Follow for more founder insights: LinkedIn → / panidawayrojpitak Instagram → / panidawayrojpitak YouTube → / @panidawayrojpitak Listen on your preferred podcast app: https://podcasters.spotify.com/pod/sh... Business inquiries & guest bookings: [email protected] Disclaimer: This podcast provides educational content only and is not a substitute for professional, legal, financial, health, or business advice; we are not liable for any decisions or actions taken based on our discussions. © Copyright Panida Wayrojpitak 2026.

Stop Using AI. Start Building With It.

Stop Prompting Claude. Use Karpathy's Method Instead.

Claude Sonnet 5, Mythos 6 ALREADY?, GPT-5.6 This Thursday, Sakana Fugu Beats Mythos, & More! AI NEWS

People Keep Asking Me About Racism In Germany. Here’s My Honest Answer.

AI Insider: The Fastest Way To Use AI Agents In Your Business, Content & Life (Open Claw & Claude)

I Stopped Chasing Leads and Built This Instead

Deep Work Music | Ocean View Productivity Beats for Hyper Focus and High Performance Flow

Ex-Amazon AI Leader: In 1 Year, the Gap Between AI Users and Everyone Else Will Be Irreversible

ART SCREENSAVER FOR YOUR TV | NO MUSIC | 2Hour | Abstract neutral art

Designing Data-Intensive Applications: Chapters 1 and 2

Why Do Predators Ignore Sleeping Humans?

The Trillion-Dollar Lie: How Elon Musk Actually Got Rich | w/ Prof. Richard Wolff

Become AI Native in less than 60 mins

I Think They Are Lying To You

Professor Jiang: World War 3 Is About To Begin, Let Me Explain!

Psychology of People With Extremely High IQ

The AI Spending Collapse Has Already Begun…

IT’S OVER: Canada Just Handed the Pentagon Divorce Papers

Building an AI Dark Factory: A Codebase That Writes Its Own Code, Live

