scripod.com

Ep 867: 2026 LLM Cheat Code: 10 Essential Steps To Get the Most out of Any AI Chatbot (Start Here Series Vol 26)

Shownote

This is the Everyday AI episode we probably shoulda done a while ago.... Because as different as ChatGPT, Gemini, Claude and others actually are under the hood, they have really started to copycat each other over the past 6 months. Which means we final...

Highlights

Jordan Wilson presents a practical 10-step framework for getting better results from any major AI chatbot, despite rapid model changes and growing similarities among platforms.
04:28
Universal rules for increasingly similar AI models
06:50
Choose an AI operating system
11:20
The real AI race is moving underneath the surface
15:16
An LLM is a reasoning engine, not a chatbot
18:16
AI is moving to the desktop
20:20
Real outputs require paid models
22:25
Context is everything the model can see
28:09
Prompting should steer the model with the right context
30:43
Connectors can carry context across applications
33:03
Governance is permission design, not paperwork
36:40
The middle steps matter most
39:30
From chatbots to commanding AI agents

Chapters

Keeping up with AI changes
00:00
Introduction to AI chatbots essentials
03:55
Rapid innovation in AI models
09:05
Understanding early AI models
13:01
Choosing an AI operating system
14:37
Discussing desktop app benefits
17:08
Understanding the context layer
21:14
Challenges without web search integration
23:55
Advancements in CRM connectors
28:55
Challenges with AI governance
32:35
Importance of observability in workflows
35:13
Developing universal AI skills
37:36

Transcript

Jordan Wilson: Welcome to the Everyday AI Podcast. My name is Jordan Wilson and for the past three and a half years, we've put out more than 800 episodes. Yet, one of the most common questions I get, I didn't really have an answer for. Where do I start on ...