Early Adoptr

The EU AI Act's Article 50 transparency rules are already in force, and they apply to your business whether you're in Dublin or Denver. But what does it actually mean? Do you need to label every piece of AI-generated content? Is your website chatbot regulated? And why is Anthropic watermarking Claude’s output?This week on Early Adoptr, Jess and Kyle are joined by Dr Barry Scannell, Partner at Irish law firm William Fry and an AI law and copyright specialist, to seperate the reality from the online noise around Article 50 of the EU AI Act, the new rules around transparency for AI systems and AI-generated content.In the episode, Barry explains the distinction between an AI provider and deployer, where most Article 50 obligations sit, and why ordinary AI-assisted copy or image editing does not automatically require a disclosure.They also unpack Anthropic’s watermarking of Claude-generated text, the limits of AI-detection tools such as Pangram, copyright risks around AI-generated code and writing, and the narrower legal definition of a deepfake under the EU AI Act.If you run a small business, use AI in marketing, commission work from agencies, operate a chatbot, or are trying to develop a responsible AI policy, this might be one of the most important episodes you listen to all year.PS. We had some technical issues on this episode, so we apologise for the audio quality! A big thanks to friend of the pod Bobby Vasquez for his audio engineering support. How to find Barry:LinkedIn: https://www.linkedin.com/in/dr-barry-scannell-bbb5aa207/How to Be a Good Human in the Loop with AI: https://earlyadoptr.ai/episodes/how-to-be-a-good-human-in-the-loop-with-aiWhat You'll Learn:What Article 50 of the EU AI Act covers and why it matters beyond the EUThe difference between an AI provider and an AI deployerWhen branding or commissioning an AI chatbot could make your business a providerWhy the transparency burden generally falls on AI companies and system providersWhat counts as a deepfake under the Act and what doesn'tWhether AI-generated social captions, ads, Canva edits, and synthetic content need a labelHow to disclose AI-generated deepfakes through labels, watermarks, metadata, or platform toolsWhy Anthropic’s text watermarking may go further than EU guidance requiresWhy AI-generated material may not receive copyright protection in many jurisdictionsWhy AI-detection tools should not be treated as conclusive proofHow AI literacy and responsible use can become a competitive advantageResources:EU AI Act: https://artificialintelligenceact.eu/article/50/Article 50 Obligations: https://www.williamfry.com/knowledge/part-1-ai-act-articles-501-and-502-transparency-obligations/EU AI Transparency Toolkit: https://www.simmons-simmons.com/en/products/eu-ai-act-transparency-toolkitFAQs: https://digital-strategy.ec.europa.eu/en/faqs/transparency-obligations-under-article-50-ai-actAnthropic watermarks Claude's output: https://aiweekly.co/alerts/anthropic-adopts-eu-ai-act-code-watermarks-claude-outputGet in Touchhello@earlyadoptr.aiTikTok: @early_adoptrInstagram: @early_adoptrYouTube: @early_adoptrLinkedIn: https://www.linkedin.com/company/early-adoptr/https://www.earlyadoptr.ai/

We talk a lot about keeping a human in the loop, but what does that actually mean in your day to day? You read the AI output, it looks right, you approve it, and you move on. But from late 2027 that might not be enough, because Article 14 of the EU AI Act comes into full enforcement.So what does it take to be a good human in the loop? You almost certainly have the skills already, and this episode is about putting them to work.In this week's episode, Jess and Kyle get into what human-in-the-loop AI looks like in practice, the four levels of oversight, the value of domain expertise and context expertise, the five-step framework for being a good human in the loop, and how HITL skills can future proof your career.What You'll LearnWhat human in the loop actually meansWhat Article 14 of the EU AI Act means for high-risk systemsThe levels of human oversightDomain expertise and context expertiseJudgement, context and accountability as career skillsA five-step framework for owning an AI decisionHow much friction to build in, and whereWhen a recurring mistake is a system problemUse these links for a discount on the tools we recommend (and it supports the pod!)Wispr Flow - AI-powered voice dictation that works across every app on your desktop - https://ref.wisprflow.ai/early-adoptrGranola - The best AI meeting notes! New users get 100% off for their first month - https://www.granola.ai?via=early-adoptrResearch: https://www.linkedin.com/pulse/how-good-human-loophitl-ray-floyd-17znc/ https://www.itbrew.com/stories/2026/03/16/what-makes-a-good-human-in-the-loop https://www.mimasolution.com/ai-act/article-14 https://www.kiteworks.com/regulatory-compliance/human-in-the-loop-ai-compliance/ https://www.datacamp.com/blog/human-in-the-loop-hitl https://www.ibm.com/think/topics/human-in-the-loop Timestamps: 00:00 Introduction and Weekly Updates04:46 AI News of the Week: AI News: Article 50 of the EU AI Act Is Now Live07:11 Why LinkedIn and Substack Are Labelling AI Content09:07 Article 14: When Human Oversight Becomes a Legal Duty09:50 Why Oversight Matters More When AI Takes Action12:17 What Human in the Loop Actually Means13:12 Levels of AI Oversight17:59 The Role of Domain and Context Experts20:45 What Domain Expertise Means for AI Oversight25:22 Context Expertise: The Business Knowledge That Lives Only in Your Head29:46 Why Compliance Risk Lands on You, Not the AI32:31 Future-Proofing Your Career in the Age of AI34:39 Judgment, Context, and Accountability in Decision-Making41:34 The Framework for Becoming a Good Human in the LoopGet in Touchhello@earlyadoptr.aiTikTok: @early_adoptrInstagram: @early_adoptrYouTube: @early_adoptrLinkedIn: https://www.linkedin.com/company/early-adoptr/www.earlyadoptr.aiNote: The written and scripted content for this episode was created with the assistance of various AI models.

What if your AI ran entirely on a laptop you own, added nothing to your monthly bill, and never sent your data anywhere? That's local AI. It might sound too good to be true, but as token costs climb and concerns about data privacy grow, local AI and small language models could be the solution.In this episode, Jess and Kyle get into what local AI actually is, why running smaller models on your own machine has become a real option, and where it fits for a non-technical business. They cover the difference between small language models and the big cloud tools, what open weight models change, the jobs local AI is best suited to, the hardware it takes to run one, and why a hybrid of local and cloud is the right answer for almost every small business rather than going all in on either.MCP Episode:Small Language Model Episode:Enterprise Nation AI Agent WebinarWhat You'll Learn:What local AI actually meansHow running a small language model on your own laptop keeps sensitive data off a third party's serversThe difference between a small language model and the large modelsWhat "open weight" models areWhat jobs local AI is good atConsiderations for the hardware needed to run local AIWhat apps you can use to run local AIResources: Small Language Models are the Future of Agentic AIThe Ultimate Guide to Local AI and AI Agents What is Local AI: The Complete Guide to Running AI on Your Own HardwareHow to Build Local AI LM Studio OllamaOsaurusTimestamps:00:00 Introduction and Weekly Updates04:45 What Local AI Actually Means07:45 Small Language Models Explained13:55 What Open Weight Models Are and Why They Matter13:55 Understanding Open Weight Models17:31 The Rise of Local AI and Its Applications27:25 Hardware Considerations for Local AI33:17 Privacy, Control, and Cost in AI Usage34:32 The Rising Cost of Tokens37:45 Speed and Efficiency in AI Models38:57 Control and Ownership of AI Models41:02 Challenges of Running Local AI44:24 Local AI and Agents47:27 The Hybrid Approach to AI Solutions48:11 Key Takeaways for Implementing Local AI49:50 AI News of the WeekGet in Touch:hello@earlyadoptr.aiTikTok: @early_adoptrInstagram: @early_adoptrYouTube: @early_adoptrLinkedIn: https://www.linkedin.com/company/early-adoptr/www.earlyadoptr.ai

Vibe coding can build you almost anything now. A customer database, a little internal tool, a whole CRM in an afternoon. But some of those things could land you in a world of GDPR pain, and one or two you should never build at all.In this final episode of the vibe coding series, Jess and Kyle are joined again by Sean Bhardwaj to work out where the line sits for a non-technical founder. They get into why building has become the easy part while distribution (aka getting people to actually use what you make) is still the hard part. They cover what belongs in the never-vibe-code pile, how much time it really takes to learn this properly, and why the answer to whether you should comes down to what you are actually trying to do.How to find Sean Bhardwaj:https://breakthroughgrow.com/https://www.linkedin.com/in/seanbhardwaj/Vibe Coding Series:Vibe Coding for Non-Technical Founders: https://www.earlyadoptr.ai/episodes/vibe-coding-for-non-technical-founders-tools-models-and-how-to-startWhy Your AI Keeps Forgetting You (w/ Rob Webster): https://www.earlyadoptr.ai/episodes/why-your-ai-keeps-forgetting-you-and-the-folder-that-fixes-it-w-rob-websterClaude Code vs Cowork (w/ Sean Bhardwaj): https://www.earlyadoptr.ai/episodes/claude-code-vs-cowork-what-non-technical-founders-need-to-know-w-sean-bhardwajClaude Code Without the Code (w/ Sean Bhardwaj): https://www.earlyadoptr.ai/episodes/claude-code-without-the-code-a-non-developer-s-week-in-review-w-sean-bhardwajAgentic Loops: https://www.earlyadoptr.ai/episodes/agentic-loops-the-engine-behind-vibe-codingVibe Coding: What to Do After the App Is Built: https://www.earlyadoptr.ai/episodes/vibe-coding-what-to-do-after-the-app-is-builtWhat You'll LearnWhy the difficult part of building software has moved from writing the code to getting real people to actually use what you have made.The security and data questions to ask before you build anything that holds customer detailsWhat you should never vibe codeWhen an open-source tool makes more senseHow to learn vibe coding without clearing your calendar,Use these links for a discount on the tools we recommend (and it supports the pod!)Wispr Flow - AI-powered voice dictation that works across every app on your desktop - https://ref.wisprflow.ai/early-adoptrGranola - The best AI meeting notes! New users get 100% off for their first month - https://www.granola.ai?via=early-adoptrTimestamps:00:43 Introduction05:22 Wrapping the Vibe Coding Series07:50 AI in the News: AI Models Break Out of a Sandbox and Hack Hugging Face13:25 Welcome Back Sean: And We Ask the Big Question: Should You Vibe Code?16:29 Why Building Is Easy Now and Distribution Is the Hard Part21:38 The Security and Data Risk of Vibe Coding24:33 Why Vibe Coding Still Needs Human Judgement26:59 Open Source vs Vibe-Coded: The CRM Example28:43 What You Should Never Vibe Code29:59 Governance, AI Policy and When an Agent Goes Rogue34:43 How to Learn Vibe Coding Without Clearing Your Calendar40:34 Rolling AI Out Across a Whole Organisation48:19 You're Not Behind: AI Hype, ROI and Adoption53:45 Should Non-Technical Founders Just Stay in Cowork?58:43 Building Is No Longer the Bottleneck, Distribution Is01:00:56 Can Anyone Vibe Code? The Final Verdicts01:04:12 Final Reflections on the Vibe Coding SeriesResearch:https://www.wired.com/story/openai-models-escaped-containment-and-hacked-huggingface/Jack Dorsey interview: https://www.youtube.com/watch?v=YTVSwOY19Qs

So you've vibe coded an app....now what? Vibe coding gives almost anyone the ability to build a working app in an afternoon. In fact, around 63% of people building this way right now have no coding background at all. But once that app is live, the job of keeping it secure, monitored, and running for real users is as hard as it has always been, and if you don't know what you're looking for, you can open yourself to all sorts of risk.In this episode, Jess and Kyle cover what it actually takes to keep an AI-built app safe and running once it's in front of real users. They break down the concept of vibe slop, what type of security risks are common for vibe-coded apps, and the operational layer that sits between deploying an app and running it safely, including configuration, access control, monitoring, and dependencies. They also walk through a security checklist you can run before anyone else uses what you've built, and more importantly, when it's time to hand what you've built over to a professional. What You'll LearnWhat vibe slop is, and why most AI-built apps have it without their builders realisingWhy AI-generated code carries a specific category of security risksThe operational layer between building something and running it safely, covering configuration, access control, monitoring, and dependenciesA practical five-step security checklist to run through before anyone else touches what you've builtHow to tell when your app has outgrown what you can safely manage, and what that decision actually looks like in practiceUse these links for a discount on the tools we recommend (and it supports the pod!)Wispr Flow - AI-powered voice dictation that works across every app on your desktop - https://ref.wisprflow.ai/early-adoptrGranola - The best AI meeting notes! New users get 100% off for their first month - https://www.granola.ai?via=early-adoptrTimestamps:00:00 Intro04:44 Why Building With AI Is the Easy Part07:01 What Vibe Coding Actually Builds09:32 Vibe Slop: Why AI-Generated Code Isn't Ready to Launch12:24 Security Risks Vibe Coders Typically Miss15:17 What Maintaining a Vibe-Coded App Actually Involves16:17 How Real Users Actually Use a Vibe-Coded App18:00 The Hidden Layers of App Development20:59 Deployment vs Configuration: The Key Differences23:45 Access Control: Who Can Actually See Your Users' Data25:37 App Monitoring: How to Spot Problems in Your AI-Built App28:51 Dependencies: The Third-Party Code Running Inside Your App34:04 AI's Role in Development: Confidence vs Reality37:53 The Five-Step Security Checklist for AI-Built Apps40:33 Version Control and Rollbacks: How to Protect What You've Built43:52 When to Call a Developer: The Signs Your App Has Outgrown You47:07 Ongoing Maintenance: Keeping Your Vibe-Coded App Safe Over Time49:29 Key Takeaways for Safe Development53:37 Wrapping up for the Week54:09 AI in the News: Apple vs OpenAI and Paying Twice for AIRESEARCH:https://charliehills.substack.com/?_bhlid=c1b7f9fda51baf0227c089624042aaa0e89b040f https://www.wsj.com/tech/ai/vibe-coding-slop-ai-tools-e6a99394 What exactly is vibe coding? (MIT Technology Review)https://www.wired.com/story/thousands-of-vibe-coded-apps-expose-corporate-and-personal-data-on-the-open-web/https://www.wired.com/story/normie-vibe-code/https://www.itbrew.com/stories/2026/04/21/so-your-employee-made-an-app-a-vibe-coding-checklisthttps://www.kaspersky.co.uk/blog/safer-vibe-coding-2026/30306/https://www.vybe.build/blog/vibe-coding-for-non-technical-founders https://the-stack-overflow-podcast.simplecast.com/episodes/youve-vibe-coded-an-app-now-what https://www.theguardian.com/technology/2026/jul/10/apple-sues-openai-trade-secrets https://techcrunch.com/2026/07/13/satya-nadella-has-issued-a-shocking-warning-to-companies-using-ai/ Get in Touchhello@earlyadoptr.aiTikTok: @early_adoptrInstagram: @early_adoptrYouTube: @early_adoptrLinkedIn: https://www.linkedin.com/company/early-adoptr/www.earlyadoptr.ai

Agentic loops are already running in your business. If you have given an AI tool a research question, walked away, and come back to a finished brief, you have used one. The same mechanism fires a payment reminder after checking whether an invoice has actually cleared, keeps Claude Code testing its own fix until the bug is gone, and sends meeting notes straight into your to-do list the moment a call ends. In this episode, Jess and Kyle get into how an agentic loop actually runs, how it connects to AI agents and AI workflow automation more broadly, and what separates it from a basic automation. They cover the three types of loop, the compounding maths of how a loop can get expensive fast, and how to build in the right amount of human oversight without losing what makes loops useful in the first place. This is also where the vibe coding series starts to pull together: everything covered so far, the tools, the project structures, the files and folders, has been setting up for this.We also cover the launch of the ChatGPT 5.6 models. Use these links for a discount on the tools we recommend (and it supports the pod!)Wispr Flow - AI-powered voice dictation that works across every app on your desktop - https://ref.wisprflow.ai/early-adoptrGranola - The best AI meeting notes! New users get 100% off for their first month - https://www.granola.ai?via=early-adoptrVibe Coding Series: Claude Skills: https://www.earlyadoptr.ai/episodes/claude-skills-explained-how-to-stop-repeating-yourself-in-every-session https://www.earlyadoptr.ai/episodes/claude-code-without-the-code-a-non-developer-s-week-in-review-w-sean-bhardwaj https://www.earlyadoptr.ai/episodes/claude-code-vs-cowork-what-non-technical-founders-need-to-know-w-sean-bhardwaj https://www.earlyadoptr.ai/episodes/why-your-ai-keeps-forgetting-you-and-the-folder-that-fixes-it-w-rob-webster https://www.earlyadoptr.ai/episodes/vibe-coding-for-non-technical-founders-tools-models-and-how-to-start What You'll Learn: What an agentic loop actually is, how it connects to AI agents and AI workflow automation more broadlyHow loops are from a basic prompt-and-response exchange or a standard automationThe three types of loopThe three things every loop needs to workWhy a vague goal compounds quicklyHow to improve a loop over timeWhy cost and overbuilding are the biggest risks Where the human in the loop still sitsTimestamps: 00:50 Introduction and Personal Updates07:36 What an Agentic Loop Is and Why It Powers Vibe Coding11:01 The Three Things Every Loop Needs to Work15:23 Scheduled, Event-Triggered, and Goal-Based: The Three Types of Loop16:32 Loops vs Basic Automations18:56 The Importance of Human In the Loop20:43 Improving Your Loop Over Time24:55 What loops look like in practice30:52 What loops take off your plate31:46 Where loops go wrong36:46 The Importance of Oversight in Automation37:43 Keeping Loops Simple and Effective41:39 Practical Takeaways for Implementing Loops45:11 News of the Week: ChatGPT 5.6 Models47:05 What's next in the vibe coding seriesResources: https://www.lennysnewsletter.com/p/how-i-ai-how-to-write-ai-agent-loopshttps://haystack.deepset.ai/blog/context-engineering https://code.claude.com/docs/en/agent-sdk/agent-loop https://martinfowler.com/articles/exploring-gen-ai/humans-and-agents.html https://blogs.oracle.com/developers/what-is-the-ai-agent-loop-the-core-architecture-behind-autonomous-ai-systems https://arxiv.org/html/2607.01641v1 https://www.theverge.com/ai-artificial-intelligence/963464/openai-gpt-5-6-codex-chatgpt-work Get in Touchhello@earlyadoptr.aiTikTok: @early_adoptrInstagram: @early_adoptrYouTube: @early_adoptrLinkedIn: https://www.linkedin.com/company/early-adoptr/www.earlyadoptr.ai

Last week, Kyle and special guest Sean debated whether Claude Code is worth switching to if you don't know how to code. The answer was: it depends. So Sean spent the following week finding out. In this episode, it's the second part of our interview with Sean. Kyle and Sean to go through what actually happened when Sean used Claude Code for a week, including the modes that made Claude Code manageable, the controls that give you more say over how it works, and where it still falls short of Cowork for everyday work. Plus, Jess is back from Cannes Lions with a round-up of what the advertising industry is saying about where AI is heading.Vibe Coding Series: Part 1 of Sean's interview: https://shows.acast.com/early-adoptr/episodes/claude-code-vs-cowork-what-non-technical-founders-need-to-knBasics of Vibe-coding: https://shows.acast.com/early-adoptr/episodes/vibe-coding-for-non-technical-founders-where-things-actuallyHow to set up your files & folders for vibe-coding: https://shows.acast.com/early-adoptr/episodes/your-ai-keeps-forgetting-everything-heres-how-to-fix-it-w-roHow to find Sean:https://breakthroughgrow.com/https://www.linkedin.com/in/seanbhardwaj/Use these links for a discount on the tools we recommend (and it supports the pod!)Wispr Flow - AI-powered voice dictation that works across every app on your desktop - https://ref.wisprflow.ai/early-adoptrGranola - The best AI meeting notes! New users get 100% off for their first month - https://www.granola.ai?via=early-adoptrIn this episode:How Claude Code's modes (plan, think, auto) work and which to reach forRunning several tasks at the same time and what it does to your output speedMonitoring and automation: setting Claude Code to act when something changesManaging how much effort Claude Code puts in and avoiding burning through your usageComparing Claude Code and Cowork: what each one is actually better atSean's week-long experiment switching exclusively to Claude CodeJess's round-up from Cannes Lions 2026 and what was different about AI conversations this yearTimestamps:00:00 - Introduction, Cannes Lions and the Claude Fable 5 update11:06 - What agents actually are in Claude Code13:26 - Plan mode, thinking mode and auto mode19:28 - How Claude Code can work on several things at once27:26 - Making the most of your Claude Code usage28:42 - Set it and forget it: monitoring with Claude Code31:05 - Why batching your focus time matters33:11 - Setting Claude Code to watch for something and act when it happens35:39 - The Claude Code controls that give you more say over how it works38:20 - How to stop Claude Code from using more than you need41:13 - Cowork vs Claude Code: Sean's verdict46:14 - Quick wins for non-technical users47:28 - Why Sean made the switch47:52 - One week in Claude Code: what actually happened50:28 - How to check in on a running Claude Code session from your phone53:20 - How skills work in Claude Code56:09 - Why thinking through what you want before Claude starts gets better results58:58 - When Claude Code overdoes it and Cowork is the simpler choice01:02:07 - Where AI tools like Claude Code are heading nextGet in Touchhello@earlyadoptr.aiTikTok: @early_adoptrInstagram: @early_adoptrYouTube: @early_adoptrLinkedIn: https://www.linkedin.com/company/early-adoptr/www.earlyadoptr.ai

If you use Cowork and talk to anyone slightly more technical about what you're doing with AI, you've probably heard it. "Just use Claude Code." Maybe more than once. And when you've tried to figure out whether that advice actually applies to you, the answers have been some version of "it depends." That's not helpful when you've never written a line of code and you're trying to make a sensible decision about your tools.In this week's episode, Kyle is joined by Sean Bhardwaj, Managing Partner at Breakthrough Growth Partners and returning guest on the show, to work through what the difference between Cowork and Claude Code actually is and whether switching is worth it for someone who is non-technical. Sean has been using AI tools to build real things in his business without a developer on hand, so his experience is more useful here than a purely technical take would be.Together they cover why Cowork's constraints exist and what they protect you from, what you gain in Claude Code, the framework for deciding which one to reach for, and the one setup rule that removes most of the risk if you do decide to make the move.How to find Sean:https://breakthroughgrow.com/https://www.linkedin.com/in/seanbhardwaj/Use these links for a discount on the tools we recommend (and it supports the pod!)Wispr Flow - AI-powered voice dictation that works across every app on your desktop - https://ref.wisprflow.ai/early-adoptrGranola - The best AI meeting notes! New users get 100% off for their first month - https://www.granola.ai?via=early-adoptrWhat You'll Learn:Why Cowork and Claude Code are not the same environment and why that distinction mattersWhat Cowork's sandbox actually protects you from (and why it's intentional)What you gain in Claude Code that you can't get in CoworkThe framework for choosing between the two depending on what you're buildingThe one setup rule that removes most of the risk in Claude CodeWhat staging and production actually meanWhy VS Code makes Claude Code feel far less intimidatingHow vibe coding works on an existing codebase, not just when starting from scratchTimestamps:00:00 Introduction01:41 Reintroducing Sean Bhardwaj04:26 Sean's journey as a non-technical vibe coder07:04 How far vibe coding can actually take you09:57 Why Cowork beats basic chat for knowledge work12:04 Folder structure and context14:20 What Claude Code gives you that Cowork doesn't17:04 Where Cowork's limits are19:50 Deciding Between Co-Work and Code25:13 When to use Cowork vs. Claude Code28:42 How much coding do you need to know?30:09 How to set up Claude Code safely33:25 The Importance of Setup: Staging vs. production35:50 Navigating Existing Code Bases vs. Starting Fresh38:07 The Role of Agents in Coding and Co-WorkGet in Touchhello@earlyadoptr.aiTikTok: @early_adoptrInstagram: @early_adoptrYouTube: @early_adoptrLinkedIn: https://www.linkedin.com/company/early-adoptr/https://www.earlyadoptr.ai/

AI has a memory problem. It is exceptionally capable within a session, helping you draft a pitch, review a contract, and write a client proposal in the same afternoon, but close the tab and it forgets everything. Open a new chat and you are back to square one, re-explaining who you are and what you do from scratch, every time, until it still never quite sounds like you.This week, Rob Webster, founder of TAU Marketing Solutions, joins Jess and Kyle to explain why this happens and how a simple file and folder structure gives your AI permanent, reliable context, so you stop losing ground at the start of every session.What You'll LearnWhy AI tools lose context between sessionsWhy folder-based context is better than any system promptThe difference between always-on context (the things permanently true about you, your role, and your business) and situational context you load in only for specific tasks or clientsHow to build a simple folder structure , what files to put in it, and how tools like Claude read that context automatically so you don't have to paste it in every timeHow to decide what information should live permanently in your files versus what's transitory context that should be removed once a project or idea is doneWhat "context drift" is and why long conversations degrade even when you've done the setup correctly — and how to catch it earlyHow this same folder structure becomes the foundation for more advanced AI work, including Claude Cowork and building your own AI agentsRob Webster - https://www.linkedin.com/in/digitalstrategyleader/ TAU Marketing Solutions - https://taums.ai/ Use these links for a discount on the tools we recommend (and it supports the pod!)Wispr Flow - AI-powered voice dictation that works across every app on your desktop - https://ref.wisprflow.ai/early-adoptrGranola - The best AI meeting notes! New users get 100% off for their first month - https://www.granola.ai?via=early-adoptrTimestamps:00:00 Introduction03:48 Why Boring AI Habits Beat Impressive Ones08:23 Two Kinds of Context: Always On vs Load When You Need It10:50 Reintroducing Rob Webster12:57 Why AI Forgets Everything Between Sessions16:43 What You're Losing Every Time You Open Claude Without Context22:37 Context Drift: Why AI Outputs Get Worse the More You Use It25:52 How to Start Giving Your AI Context About Who You Are32:01 Making It Stick: Naming Chats, Pinning Projects, Starting Your Folders35:28 What a Working Folder Structure Actually Looks Like37:04 Where to Store Your AI Context Files (Local vs Cloud)46:40 Global vs Project-Specific: The About Me Folder and Beyond53:47 How AI Reads Context56:12 How This Scales Into Agents, Claude Code, and Vibe CodingGet in Touchhello@earlyadoptr.aiTikTok: @early_adoptrInstagram: @early_adoptrYouTube: @early_adoptr