Talking about prompts and chatbots won't help you talk about AI strategy in 2026.

You've gotta know the ins and outs of loops, plans, goals, subagents and more.

In this episode of Everyday AI, we're breaking down the agent lingo and how the key terms play out in systems like Codex and Claude Desktop.

Desktop Agent Lingo Simplified: Goals, Loops, Plans, Subagents and how it works in Codex and Claude Code -- An Everyday AI Chat with Jordan Wilson

Newsletter: Sign up for our free daily newsletter
More on this Episode: Episode Page
Today's Episode on LinkedIn: Thoughts on this? Join the convo on LinkedIn and connect with other AI leaders.

Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Website: YourEverydayAI.com
Email The Show: info@youreverydayai.com
Connect with Jordan on LinkedIn

Topics Covered in This Episode:

1. Desktop Agent Vocabulary Primer
2. Agent Harnesses: Codex vs. Claude Code
3. Desktop Agent Plans: Features and Workflow
4. Goal Setting in Codex and Claude Desktop
5. Plan vs. Goal: Key Differences
6. Agent Loops: Automation and Verification
7. Sub Agents: Parallel Task Management
8. Context Windows and Task Delegation
9. Guardrails, Verification, and Cost Control
10. Transition from Chatbots to Autonomous Agents

Timestamps:

00:00 Shifting focus to AI agents

03:28 Accessing the Start Here series

09:31 Using plan mode in clawed desktop

12:04 Understanding plan vs. goal mode

14:25 Setting project goals and planning

19:33 Accessing Start Here series

22:03 Building effective training loops

26:48 Managing sub agents effectively

27:30 Setting up sub-agent system

30:47 Closing and subscription reminder

Keywords:

desktop agent, desktop AI agent, agent lingo, agent vocabulary, long running agent, autonomous agent, codex, Claude Code, Claude desktop, AI harness, agentic harness, agentic tools, super app, Microsoft super app, OpenAI codex, long running desktop agents, plan mode, planning phase, agent plan, goal setting, AI goal, agent goals, loop mode, agent loops, scheduled automations, sub agents, agent subagents, context windows, parallel work, context hygiene, verification steps, approval points, skills, automations, API token usage, project threads, co work tab, code tab, work trees, checkpoints, file access, browser automation, human in the loop, token efficiency, agent delegation, AI supervision, knowledge work automation, AI subagent management, desktop agent mental model, computer control, AI project management, AI workload delegation, remote steering, front end chatbot, proactive AI, AI context sharing.

Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

Start Here ▶️

Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com

Also, here's a link to the entire series on a Spotify playlist.

Ever wish your agent would just watch you work and copy you? 👯

Oh wait, that's exactly what OpenAI released.

The new 'Record and Replay' feature in Codex allows you to simply record anything you do and turn it into a repeatable workflow for your agents.

Join us LIVE as we show you how. ⏺️

Codex Record and Replay: How to Teach an Agent Once Your Most Time-Consuming Workflows -- An Everyday AI Chat with Jordan Wilson

Newsletter: Sign up for our free daily newsletter
More on this Episode: Episode Page
Today's Episode on LinkedIn: Thoughts on this? Join the convo on LinkedIn and connect with other AI leaders.

Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Website: YourEverydayAI.com
Email The Show: info@youreverydayai.com
Connect with Jordan on LinkedIn

Topics Covered in This Episode:

1. Codex Record and Replay Feature Overview
2. Transition from Prompting to Demonstration
3. Skill Markdown Files as Business Artifacts
4. Codex vs Claude Desktop Agent Comparison
5. Workflow Recording and Security Best Practices
6. Step-by-Step Codex Record and Replay Demo
7. Video Understanding Capability in Codex
8. Editing and Sharing Skills Across Platforms
9. Automating Multi-App, Cross-System Workflows
10. Validation, Scheduling, and Automation of Skills

Timestamps:

00:00 OpenAI's record and replay feature

04:41 Preparing for screen sharing

08:56 Managing Small Tasks Efficiently

10:03 Automating top story analysis

15:43 Debating AI business strategies

18:29 Codec's video ingest feature

22:01 Practicing low stakes automation

24:57 Using skills and plugins efficiently

26:19 Using Chattopty for workflow automation

Keywords:

codex record and replay, OpenAI record and replay, record and replay feature, codex workflow automation, proactive AI agents, skill.md file, skill markdown file, editable skill files, demonstration over prompting, desktop AI agents, Mac AI features, video ingestion AI, video understanding by AI, cross-platform AI workflows, AI workflow scheduling, codex plugins, codex Chrome profile, AI screen recording, reusable AI skills, skill file cross-compatibility, Claude desktop import, Google Gemini video support, AI workflow privacy, enterprise AI permissions, low stakes workflow automation, scheduled AI automations, computer use access, browser automation AI, AI handling Chrome profiles, prompt engineering replacement, automation library, validation of AI skill files, skill validator, PyYAML error handling, skill replay, Codex versus Claude, multi-app workflow automation, real business artifact AI, automation success criteria, desktop program integrations, computer task recording, mundane workflow automation, non-technical AI setup, AI scheduled worker, AI skill refinement

Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

Start Here ▶️

Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com

Also, here's a link to the entire series on a Spotify playlist.

Is the open model GLM-5.2 really Opus 4.8 level? 🤯

You mighta missed this, but over the past few weeks, three distinct forces have all converged at one:

↳ Chinese open models are near frontier SOTA
↳ Microsoft is reportedly considering open models to run Copilot
↳ Enterprises everywhere are talking token efficiency as AI costs soar

So while many are watching GLM-5.2 as an isolated model, it's important we dive deeper on its wider implications.


Open Source Surge? Does GLM-5.2 Make Open Source an Enterprise Priority? -- An Everyday AI Chat with Jordan Wilson

Newsletter: Sign up for our free daily newsletter
More on this Episode: Episode Page
Today's Episode on LinkedIn: Thoughts on this? Join the convo on LinkedIn and connect with other AI leaders.

Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Website: YourEverydayAI.com
Email The Show: info@youreverydayai.com
Connect with Jordan on LinkedIn

Topics Covered in This Episode:

1. Open Source AI's "ChatGPT Moment"
2. GLM 5.2 Model Benchmarks & Performance
3. Enterprise Adoption Drivers for Open AI
4. Microsoft Evaluating DeepSeek for Copilot
5. Token Maxing to Token Efficiency Shift
6. GLM 5.2 Infrastructure vs. Consumer Use
7. Autonomous Workflow Overshoot Explained
8. Capability Gap and Workflow Challenges
9. Enterprise Scenarios for Open Source Models
10. Future of Task-Specific SOTA AI Models

Timestamps:

00:00 Open source AI catching up

04:52 Enterprise shift to DeepSeek models

08:57 Comparing AI model performances

12:46 Running AI models locally

14:17 Open source model cost efficiency

17:37 Cost challenges with AI models

21:05 Agentic task token consumption

25:05 Introducing the Start Here series

27:58 Impact of AI on Job Roles

32:29 Evaluating Open Source AI Models

36:00 Considering open source models

37:09 Future of open source AI

Keywords:

open source AI, open source AI models, GLM 5.2, z AI, Zhipu AI, Chinese open source models, DeepSeek, Microsoft, enterprise AI, token maxing, token efficiency, AI spend, AI deployment, open weight models, proprietary AI models, AI benchmarks, Artificial Analysis Intelligence Index, enterprise infrastructure, agentic workflows, coding tool use, autonomous agents, long context window, coding capabilities, API costs, AI privacy considerations, model distillation, data privacy, compute requirements, GPU infrastructure, AI hardware, API hosting, Hugging Face, AWS, AI cost reduction, Copilot Cowork, Azure security, Anthropic, OpenAI, Claude Opus, multimodal models, task-specific AI models, model capability gap, autonomous workflow overshoot, agentic tasks, non-agentic tasks, state of the art open models, model fine-tuning, small language models, AI adoption barriers, frontier models, AI job automation, workflow transformation, AI subsidies, token billing, Stanford AI study, AI industry trends

Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

Start Here ▶️

Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com

Also, here's a link to the entire series on a Spotify playlist.

ChatGPT tasks are back, Jack. ✅

While we were collectively ping-ponging the Anthropic vs. U.S. government saga, the big tech AI players rolled out a TON of fresh AI features that are available today.

↳ Claude Design got a big upgrade
↳ Google Vids got some serious AI sparkle
↳ And there's a new Open Weights model king

We'll break it all down.


ChatGPT’s Task Comeback, Claude’s Design upgrade, Codex Copies your workflow and 7 other Fresh AI features you’ll Want to use Today -- An Everyday AI Chat with Jordan Wilson

Newsletter: Sign up for our free daily newsletter
More on this Episode: Episode Page
Today's Episode on LinkedIn: Thoughts on this? Join the convo on LinkedIn and connect with other AI leaders.

Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Website: YourEverydayAI.com
Email The Show: info@youreverydayai.com
Connect with Jordan on LinkedIn

Topics Covered in This Episode:

1. ChatGPT Pulse Sunsetting and Tasks Comeback
   2. ChatGPT Scheduled Tasks Features and Access Tiers
   3. Claude Design June Update Overview
   4. WYSIWYG Editing and Design System Imports in Claude Design
   5. Claude Design Export Options and Third-Party Integrations
   6. Google Vids AI Avatars Upgrade with Veo 3.1
   7. OpenRouter Fusion Multi-Model Synthesis Feature
   8. Claude Code Artifacts for Team and Enterprise Plans
   9. GLM 5.2 from ZAI Open Weights Model Overview
   10. GLM 5.2 Benchmarks and Enterprise Use Cases
   11. OpenAI Codex Record and Replay Feature Explained
   12. Codex Record and Replay vs. Traditional RPA Tools
   
   
   

Timestamps:

00:00 Intro: 7 new AI features you can use today

02:35 ChatGPT Tasks: Pulse is gone, Tasks are back

04:31 Who has access to ChatGPT Tasks

08:18 Claude Design June update overview

09:14 WYSIWYG editing and Claude Code integration

12:07 Claude Design export options and third-party integrations

15:21 Google Vids AI Avatars upgrade

18:15 OpenRouter Fusion multi-model synthesis

21:54 Claude Code Artifacts for teams

25:36 GLM 5.2 from ZAI open weights model

29:02 OpenAI Codex Record and Replay

Keywords:

ChatGPT Tasks, ChatGPT Pulse, OpenAI, scheduled tasks, proactive AI agent, Claude Design, WYSIWYG editor, Claude Code, design system import, PowerPoint export, Google Vids, AI avatars, Veo 3.1, Gemini 3.1 Flash, OpenRouter Fusion, model fusion, multi-model synthesis, Claude Code Artifacts, Claude Team plan, GLM 5.2, ZAI, open weights, MIT license, mixture of experts, Codex Record and Replay, RPA, workflow automation, Artificial Analysis, Hugging Face, Canva integration

Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

Start Here ▶️

Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com

Also, here's a link to the entire series on a Spotify playlist.

The Fable 5 drama continues.... but what does it really mean? 🤔

Anthropic released the most powerful AI model in the world, only for it to be pulled worldwide days later over bio and cyber concerns.

Sound like a tough break, right?

But, was the writing on the wall all along? Was Anthropic asking for this type of regulation? And what does the future of heavy-handed government regulation mean for your company and its AI strategy?

We'll tackle it all, LIVE.

Fable 5 Drama Updates: The latest Between Trump vs. Anthropic and How it Impacts You -- An Everyday AI Chat with Jordan Wilson

Newsletter: Sign up for our free daily newsletter
More on this Episode: Episode Page
Today's Episode on LinkedIn: Thoughts on this? Join the convo on LinkedIn and connect with other AI leaders.

Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Website: YourEverydayAI.com
Email The Show: info@youreverydayai.com
Connect with Jordan on LinkedIn

Topics Covered in This Episode:

1. What Are Fable V and Mythos V: Differences Explained
   2. Anthropic's Pre-IPO Timeline From April Through June
   3. The Government's Export Control Directive: What It Said
   4. Anthropic's Blog Post Response vs. David Sacks' Rebuttal
   5. Amazon CEO Andy Jassy's Role in Triggering the Crackdown
   6. China-Linked Access and the Geopolitical Stakes
   7. Day-by-Day Breakdown: Friday Through Wednesday
   8. Reactions From Alex Stamos, Yann LeCun, Jeremy Howard
   9. CyberGym Benchmark and Microsoft's MDash Comparison
   10. Safety Theater Accusations Against Anthropic
   
   

Timestamps:

00:00 Fable V drama overview and why it matters

01:35 Big picture recap and episode roadmap

03:51 Fable V vs. Mythos V explained, Project Glasswing

05:01 Anthropic's pre-IPO hype timeline April to June

06:31 Friday: government directive and global shutdown

07:53 Pre-IPO context: SpaceX comparison and market stakes

11:42 Background: February Pentagon dispute origins

13:48 Friday export directive and Anthropic's blog post statement

16:19 David Sacks rebuttal read in full

21:48 G7 summit, Amazon's role, and the China connection

26:57 Tuesday security letter and Wednesday Wired report

30:59 Industry reactions: LeCun, Stamos, Howard, Ottenheimer

36:44 Jordan's full hot take: Anthropic's IPO chess game

43:09 What your company should do now

Keywords:

Fable V, Mythos V, Anthropic, Dario Amodei, export control directive, jailbreak, national security, Howard Lutnick, David Sacks, Andy Jassy, Project Glasswing, Anthropic IPO, US government, Trump White House, Pete Hegseth, Amazon AWS, CyberGym benchmark, Microsoft MDash, Yann LeCun, AI safety theater, frontier AI, enterprise AI strategy, fallback models, G7 summit AI, geopolitics AI

Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

Start Here ▶️

Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com

Also, here's a link to the entire series on a Spotify playlist.

For 799 episodes, we’ve cut it to you straight on AI.

(Episode 800 will be no different.)

To celebrate our 800th episode, we took a ‘State of AI’ type look across the sector and broke down three big categories:

8 Uncomfortable AI Truths, 10 Moves Smart Teams Are Making, 10 Questions Every AI Leader Must Ask.

Join us as we break it all down.

Celebrating our 800th Episode: 8 AI Truths, 10 Smart AI Moves and 10 Questions You Must ask — An Everyday AI Chat with Jordan Wilson

Newsletter: Sign up for our free daily newsletter
More on this Episode: Episode Page
Today's Episode on LinkedIn: Thoughts on this? Join the convo on LinkedIn and connect with other AI leaders.

Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Website: YourEverydayAI.com
Email The Show: info@youreverydayai.com
Connect with Jordan on LinkedIn

Topics Covered in This Episode:

1. Eight Uncomfortable AI Truths for Leaders
2. AI Model Risk: Single-Model Dependency
3. Moats Shifting to AI Operating Layers
4. Workflow Design vs. Prompting in AI
5. Static Business Artifacts Becoming AI Debt
6. Workflow Automation and AI Task Reshaping
7. Open Weight Models as AI Resilience
8. Agentic AI: Operational vs. Theoretical Risks
9. Ten Smart AI Team Moves Explained
10. Portable AI Stack Building Strategies
11. Workflow Mapping Before AI Tool Adoption
12. Building Role-Specific AI Skill Packs
13. Automating Reports and Briefings with AI
14. Converting Static Files to Living Artifacts
15. AI Agent Deployment: Read-Only Mode Testing
16. Routing Work by Model Value and Cost
17. Measuring AI Output Quality, Not Activity
18. Red Teaming AI Workflows Beyond Models
19. Capturing AI Decision Reasoning for Business
20. Ten Critical AI Questions for Leaders

Timestamps:

00:00 Episode 800: 8 AI Truths, Leader Moves

05:40 Rising Trend of AI Super Apps

07:37 AI series and future capabilities

13:01 Challenges of AI Implementation

14:33 Impact of AI on Work Processes

19:44 Microsoft's open-source AI strategy

23:24 Avoiding shiny new AI tools

25:44 Using marketing skill packs

29:38 Criticism of human-in-the-loop systems

33:44 Managing AI and Cost Efficiency

35:50 Evaluating AI content effectiveness

40:15 Key questions for leaders

42:35 Challenges in AI workflow management

44:52 Evaluating AI costs and outputs

48:20 The rise of AI capabilities

Keywords:

AI truths, AI workflow automation, generative AI, artificial intelligence, AI model risk, single model strategy, business continuity, model export control, government AI policy, operating layer, AI super apps, codex, unified memory, large language models, agentic AI, workflow design, AI prompting, scheduled tasks, AI skills, context engineering, static business artifacts, organizational debt, AI native deliverables, autonomous AI, AI job redesign

Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

Start Here ▶️

Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com

Also, here's a link to the entire series on a Spotify playlist.

Ready for the AI buzzword for the rest of 2026?

Superapps.

No, not China’s WeChat.

The AI Superapp era is much different, and it’s about to hit the business world hard. So, if you aren’t sure what an AI Superapp is or if your company should be using one, this is an episode you can’t miss.

AI SuperApps: Why Every Company is Racing to Create One and What They are — An Everyday AI Chat with Jordan Wilson

Newsletter: Sign up for our free daily newsletter
More on this Episode: Episode Page
Today's Episode on LinkedIn: Thoughts on this? Join the convo on LinkedIn and connect with other AI leaders.

Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Website: YourEverydayAI.com
Email The Show: info@youreverydayai.com
Connect with Jordan on LinkedIn

Topics Covered in This Episode:

1. AI Super App Race: OpenAI, Anthropic, Microsoft
2. What Is an AI Super App? Explained
3. Agentic Shift: Chatbots to Autonomous Coworkers
4. Super App Harness vs. AI Model as Moat
5. Three-Pane Super App Interface Innovation
6. Codex vs. Cursor vs. Claude Benchmarks
7. Enterprise Desktop Integration and Super App Strategy
8. Super App Security, Risks, and Best Practices

Timestamps:

00:00 Super app race and ChatGPT integration

06:04 Emergence of desktop super apps

08:41 Codex as the leading super app

11:22 Shift to AI desktop super apps

14:13 The AI super app's proactive updates

17:26 Token efficiency in super apps

21:29 Future of AI model usability

27:03 Anthropic's role in AI development

30:19 Google's Gemini 3.5 and Anti-Gravity Launch

33:13 Risks and responsibilities with AI apps

34:31 Cautionary advice on AI usage

38:03 Introduction to AI super apps

Keywords:

AI super app, AI superapps, super app era, desktop super app, agentic AI, autonomous coworker, agentic context carry, agentic work future, AI execution layer, super app harness, model moat, code interpreter, Codex, OpenAI super app, Microsoft super app, GitHub Copilot, Anthropic, Claude Code, Claude Cowork, Google anti gravity, Gemini 3.5 Flash, Cursor, desktop agentic coworker, unified memory, files automations, approvals and automations, browser control, computer use, three pane interface, context engineering, prime prompt polish, token efficiency, user experience, read-write access, autonomous workflows, desktop AI companion, schedule automations, approval workflows, cross-app integration, enterprise adoption, permission controls, role based access, sandboxing, expert-driven loop, AI safety, risk management, computer automation, enterprise AI strategy, AI model integration, productivity automation

Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

Start Here ▶️

Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com

Also, here's a link to the entire series on a Spotify playlist.