Welcome to Episode 28 of CTRL-ALT-DEV! Today, Sean and Paul strip back the format for a fireside "Deep Dive" into the reality of AI-assisted software development.

With tools like Replit, Lovable, and Bolt, founders are building working software faster than ever. But there is a massive hidden gap between a shiny prototype and a production-ready application.

Because AI sounds incredibly confident and presents everything as correct, builders often don't realize the risks hiding beneath the surface. I

n this episode, we unpack why every piece of "vibe-coded" software needs a comprehensive Code Audit before it goes anywhere near real users.

Key Topics & Highlights:

• The Vibe Coder Dilemma: Vibe coders are often shrewd business owners trying to replace expensive SaaS subscriptions with their own AI-built tools. While they understand their market and price points perfectly, they often lack knowledge of the Software Development Life Cycle (SDLC).
• The Iceberg Analogy: Users see the visible 20% (beautiful dashboards and UI), but the invisible 80% below the surface holds all the risk. Paul explains the doomsday scenario: an unsupervised AI fixing a bug at 3 AM that inadvertently locks out 100 site workers the next morning.
• The 11 Pillars of Great Software: Inspired by a pre-AI developer conference, Paul details the foundational pillars of software that AI often ignores. These include security (zero-day vulnerabilities), performance bottlenecks, code maintainability, accessibility, automated testing, and proper database schemas.
• End-of-Life Compliance: When you roll an app out, it relies on hundreds of thousands of underlying packages and node modules. Paul explains how these frameworks often reach "end of life" for security updates within two years, requiring constant active maintenance.
• The £3,000/Month AI Trap: The hidden costs of auto-scaling AI apps are huge. Paul shares a story of a client spending £3,000 a month on Replit due to spaghetti code and auto-scaling. They dropped their costs to under £200 a month by exporting the code, moving to Railway for hosting, and using Claude Code.
• The True Value of AI Builders: Vibe coding is the ultimate prototyping tool. It allows founders to build an MVP, prove market demand, and even secure investment (like one user who successfully deployed a native app to TestFlight with 40-60 users). Once the prototype proves the concept, you hand the blueprint over to a professional dev team to scale safely.

Links & Resources Mentioned in this Episode

• Replit, Lovable, & Bolt: https://replit.com/, https://lovable.dev/, https://bolt.new/ (The AI-assisted development platforms mentioned for rapid prototyping and vibe coding).
• Claude Code (Anthropic): https://claude.ai/ (The AI tool Paul recommends for maintaining the codebase more affordably once exported).
• Railway: https://railway.app/ (The hosting platform mentioned where a client moved their exported app to pay just £5 a month).
• Endoflife.date: https://endoflife.date/ (Paul specifically recommends this website to check when software frameworks and dependencies stop getting security updates).
• Submit Your Questions: mailto:[email protected] (The email address provided for listeners to submit their topics or code audit requests).

Hosts: Sean Sale and Paul Rhodes Guest: Craig Hellen (Managing Director & Co-Founder, Bex Media)

Welcome to Episode 27 of CTRL-ALT-DEV! After rushing off mid-recording in Episode 25, Craig Hellen of Bex Media is back. This time, we step away from the creative outputs of AI (like voiceovers and video) and look under the hood at how Craig is using AI as a deep "operating layer" across finance, operations, and standard operating procedures (SOPs). We dive heavily into the "Cult of Lean," exploring how to apply manufacturing efficiency principles to digital workspaces, the frustration of limited software integrations (MCPs), and how to set up an "AI Brain" that interviews you to find the hidden waste in your business.

Key Topics & Highlights:

• The World Cup Intro: A quick catch-up on the World Cup kickoff, FIFA video games, and Paul's unprecedented red card streak.
• AI as an Operating Layer: Why standard bolt-on AI tools aren't enough. Craig explains how his technical background allows Bex Media to rapidly test and deploy AI to reduce duplication and rework across their entire project management system.
• The Cult of Lean: Craig breaks down his "penny drop" moment with Lean methodology. We discuss the 8 Wastes of Lean—specifically overproduction, excess processing, and the massive underutilization of talent in the AI era.
• The Changing Job Landscape: Paul shares his observation that AI isn't causing massive job replacements yet; instead, businesses are removing the 80% grunt work so their existing staff can pivot to human-centric roles (like sales and relationship building) to drive 20% growth.
• Real-World Waste Reduction: Craig shares a brilliant physical example of Lean: using AI to reorganize his physical studio space, reducing setup time for social media shoots from two hours down to just two minutes.
• The "AI Brain" Interview Technique: Don't just give AI a blank prompt. Paul and Craig detail a masterclass workflow: Tell Claude or Gemini that it is a Lean Consultant, give it your company context, and ask it to generate 40 interview questions to diagnose your business waste.
• The Frustration of Limited MCPs: Craig vents his frustrations with Monday.com's Model Context Protocol (MCP) limitations, which artificially block him from automating certain board creations. Paul explains why they have actively canceled over £5,000 in SaaS subscriptions simply because those tools refused to allow open AI connectivity.

Takeaway Challenge For This Week: Spend one hour with your AI tool of choice. Tell it what your business does, explain your processes, and ask it one simple question: Where is the waste?. Promised Show Notes Extras: The 8 Wastes & Your Copy/Paste Prompt During the show, Paul promised to provide a link to the 8 Wastes of Lean and a cookie-cutter prompt for listeners to use.

• Article to read: The 8 Wastes of Lean Explained
• Copy & Paste AI Prompt:

Links & Resources Mentioned in this Episode Guest Links:

• Bex Media: bexmedia.net.
• Craig Hellen on LinkedIn: https://www.linkedin.com/in/craig-hellen-8020616/

Podcasts, Books & Methodologies:

• Lean Made Simple Podcast: https://www.youtube.com/@leanmadesimple
• Two Second Lean by Paul Akers: Mentioned by Craig as the standard popular book on Lean methodology - https://www.worldofbooks.com/en-gb/products/2-second-lean-how-to-grow-people-and-build-a-book-paul-a-akers-9781466258556?sku=GOR012042001&gad_source=1&gad_campaignid=17415896148&gbraid=0AAAAADZzAIDEp7m016BaYU4vDnwJLUqK6&gclid=Cj0KCQjwi8nRBhDhARIsAHZf_pbRyDho4CfUR9-tsVJhoDZPj5BvQZq-ClReNjC06WP_njacH-Egx9AaAlRKEALw_wcB
• The Lean Startup: https://theleanstartup.com/
• Jason Fried / 37signals: https://37signals.com/podcast/guest/jason-fried/

Tools & Platforms:

• Monday.com: The work management software Craig uses as Bex Media's "home for our business online".
• Notion: The workspace app Paul uses heavily for SOPs, playbooks, and Kanban boards.
• Claude / Claude Cowork (Anthropic): The primary AI tool Paul and Craig recommend for building an "AI Brain" and connecting via MCP to sources of truth.
• Google Drive: Used by Paul as the version-controlled "gold master" source of truth for GGA's documents.
• Trello: Mentioned by Paul as a tool they completely migrated away from in just an hour using AI and Notion.
• Replit: Referenced by Paul regarding "vibe coders" who skip the planning phase and end up over-engineering

Other Resources

Submit your Admin Nightmares: mailto:[email protected]

• Paul's LinkedIn: https://www.linkedin.com/in/ukwebdevelopment/
• Sean's LinkedIn: https://www.linkedin.com/in/seansale/

Ctrl+Alt+Dev YouTube Channel: https://www.youtube.com/@ctrlaltdevpodcast

Ctrl+Alt+Dev Spotify: https://open.spotify.com/show/3NF9wHGBjqTFNowfbBbODc

Ctrl+Alt+Dev Apple Podcast: https://podcasts.apple.com/us/podcast/ctrl-alt-dev/id1825374857

Hosts: Sean Sale and Paul Rhodes

Welcome to Episode 26 of CTRL-ALT-DEV! Today, we are stripping back the format—no guests, no slides—to discuss one of the most unexpected and life-changing AI experiments we've built to date: the AI Meal Planner.

What started as a simple test to make cooking easier has morphed into a system that slashes food waste, completely eliminates duplicate supermarket purchases, and could easily save families up to £5,000 a year. We dive into the shocking reality of UK food waste, the concept of "reverse meal planning," and how Paul went from a Notion-based AI workflow to coding his own custom app in just 15 minutes.

Key Topics & Highlights:

• The Jaw-Dropping Stats on UK Food Waste: We set the scene with data from WRAP showing that UK households throw away 6 million tons of food and drink every year (costing £17 billion globally, or roughly £1,000 per family of four). A staggering 73% of this is perfectly edible food, and 80% of waste simply comes down to cooking too much or not using food in time. Surprisingly, 18-34-year-olds are the worst offenders.
• The Cost of Convenience: Sean makes a painful confession: he spent £5,000 on takeaways alone last year, bringing his total food budget to a shocking £13,000 annually. Paul shares how he used the financial app Snoop to realize he was wasting massive amounts of money on daily convenience store trips.
• Reverse Meal Planning: Why standard meal planning fails. Instead of starting with a blank sheet of paper and buying new ingredients, "reverse meal planning" starts with an inventory of what you already have in the fridge and pantry (prioritizing items that are expiring soon) and building a gap-fill shopping list from there.
• The MVP AI Workflow: Paul details his 15-minute Saturday routine: he uses Whisper Flow to audio-dictate his cupboard inventory, and then Claude Cowork scans his family's calendar, cross-references 17 digital recipe books, and pushes the required ingredients straight to Notion and the Bring! shopping app.
• From Prompt to Custom App in 15 Minutes: Using Claude Code and a solid Product Requirements Document (PRD), Paul actually built his own local meal planner app overnight to streamline the entire process, removing the need for third-party apps like Bring! and Notion.
• Scanning for UPFs (Ultra-Processed Foods): Inspired by Chris van Tulleken's book Ultra-Processed People, Paul talks about trying to eliminate UPFs. Since apps like Yuka only show nutritional scores, Paul is now integrating a custom barcode scanner into his app to cross-reference ingredients for UPFs while at the supermarket.

(Listener Challenge: Have you figured out a way to automate the checkout basket directly to Sainsbury's, Tesco, Aldi, or Ocado using AI? We are still experimenting with this and want to hear your workflows! Email us to share, or request our prompts!) -------------------------------------------------------------------------------- Links & Resources Mentioned in this Episode

Paul and Sean can be found here:

Paul Rhodes - [email protected]

https://www.linkedin.com/in/ukwebdevelopment/

Sean Sale - [email protected]

https://www.linkedin.com/in/seansale/

The Apps & AI Tools:

• Claude Cowork / Claude Code (by Anthropic): https://claude.ai (The core AI tools Paul used for the automation and to code the custom app).
• Bring!: https://www.getbring.com/ (The one-click digital shopping list app Sean and Paul use).
• Notion: https://www.notion.so/ (The workspace tool Paul used for his MVP meal and staple planning).
• Snoop: https://snoop.app/ (The financial tracking app Paul used to auto-categorize his spending and identify takeaway/grocery waste).
• Yuka: https://yuka.io/en/ (The app Paul mentions using to scan product barcodes for nutritional scores).

The Books & Recipe Inspiration:

• Ultra-Processed People by Chris van Tulleken: https://www.penguin.co.uk/books/451/451300/ultra-processed-people/9781529195461 (The book that inspired Paul's health kick and the custom UPF scanner).
• John Watts Cookbooks: https://chefjonwatts.com/books/
• The Hairy Dieters: https://uk.bookshop.org/p/books/the-hairy-dieters-eat-for-life-how-to-love-food-lose-weight-and-keep-it-off-for-good-hairy-bikers/3344347?ean=9780297870470&next=t

Reports & Research:

• WRAP (Waste and Resources Action Programme): https://wrap.org.uk/ (The organization cited by Paul for all the staggering statistics regarding the 6 million tons of UK food waste).

Resources from Sean & Paul:

• https://docs.google.com/document/d/1fpIdgZSXXWV6pjqnxpgVmh1A4NpemILQ_ztDTI2V05Y/edit?tab=t.0 https://docs.google.com/document/d/101zXuk7RTe5t-fyhBEZX2blh2j23eJd-wBm2OGNzpjs/edit?tab=t.0 https://docs.google.com/document/d/1P_xhk67b_Xxtw9ixoUz4-I967MTSNl4vseEWp7VbaGQ/edit?tab=t.0

Hosts: Sean Sale and Paul Rhodes Guest: Craig Hellen (Managing Director & Co-Founder, Bex Media) Welcome to Episode 25 of CTRL-ALT-DEV! Today, we are stepping away from software development and looking at AI adoption through a completely different lens: the creative agency. We are joined by Craig Hellen, Managing Director of Gloucestershire-based video production and motion graphics company, Bex Media. With nearly two decades of experience producing everything from international corporate videos to high-pressure live events, Craig shares how his technically inquisitive team is embracing AI. From the realities of on-set client control to the copyright trap of AI-generated logos, this episode explores what happens when generative tech collides with high-end creative processes. Key Topics & Highlights:

• The Illusion of Control in GenAI: While models like Google Omni are impressive, Craig explains why AI isn't ready to take over high-level creative production. On a live set, clients and creative directors need to make granular, real-time adjustments (like changing a specific prop's color). Currently, AI struggles with this level of specific, targeted adjustability without regenerating the entire output.
• The Voiceover Revolution: The biggest immediate shift in the video industry is AI voiceovers. Craig explains how Bex Media uses tools like ElevenLabs to generate "scratch tracks" so editors and clients can structure videos even if the final script isn't ready. To protect client IP and avoid generic voices, Bex Media designs and securely hosts exclusive AI voices for their clients rather than using pre-sampled platform voices.
• The Copyright Trap: Sean and Craig discuss a terrifying reality for marketers and agencies: under current UK/US law, copyright typically requires a human author. If you generate a brand logo entirely using AI, you might not automatically own the copyright to protect it from being stolen (though trademarking may still apply).
• Lean Methodology as an AI Framework: How do you stop your team from running wild with new AI tools? Craig shares how he uses "Lean" (originally the Toyota Manufacturing System) to provide a cultural framework and guardrails for continuous improvement and AI adoption.
• AI Companions in History: Sean shares his fascination with the "Chloe vs History" social media videos, where an AI-generated avatar interacts with historical events like the WW1 trenches or the Titanic.

(Note: While some specific entities were explicitly mentioned in the recording, standard web addresses have been provided below for your editor's convenience. You may want to independently verify these external URLs before publishing.) Guest Links:

• Bex Media: https://bexmedia.net/ (Craig's video production company).
• Craig Hellen on LinkedIn: https://www.linkedin.com/in/craig-hellen-8020616/ (You can also find his business page under /movingimage).

Tools & AI Platforms:

• ElevenLabs: https://elevenlabs.io/ (The AI voiceover platform heavily discussed by Craig and Paul for generating and hosting custom voices).
• Google Omni (Gemini): https://gemini.google.com/ (Discussed regarding how the big tech players are approaching the creative ecosystem).

Podcasts & Learning Resources:

• Lean Made Simple Podcast: https://www.leanmadesimple.com/podcast (Hosted by Ryan Tierney - mentioned by Craig as the podcast that gave him his "penny drop" moment for applying Lean principles to his business).
• The Vergecast: https://www.theverge.com/the-vergecast (One of the daily tech podcasts Craig listens to).
• CVP (Creative Video Productions): https://cvp.com/ (Mentioned by Craig for keeping up with industry tech and lens technology).

Media Referenced:

• Pepsi, Where's My Jet? (Netflix Documentary): Referenced by Paul to illustrate how clients make massive editorial decisions on set.
• Chloe vs History: The AI-generated historical social media videos discussed by Sean.

• Submit your Admin Nightmares: mailto:[email protected]
• Paul's LinkedIn: https://www.linkedin.com/in/ukwebdevelopment/
• Sean's LinkedIn: https://www.linkedin.com/in/seansale/
• Ctrl+Alt+Dev YouTube Channel: https://www.youtube.com/@ctrlaltdevpodcast
• Ctrl+Alt+Dev Spotify: https://open.spotify.com/show/3NF9wHGBjqTFNowfbBbODc
• Ctrl+Alt+Dev Apple Podcast: https://podcasts.apple.com/us/podcast/ctrl-alt-dev/id1825374857

Welcome back to Part 2 of our fantastic conversation with Luke Passmore from Yellow Box Software!

Last week we talked about the difference between building software that looks good in a demo versus software that survives in the real world. Today, we go even deeper into the messy reality of tech implementation. We explore Luke's "red flag" sheet for new clients, the real value of AI in manufacturing (forecasting), and a terrifying story about an autonomous AI that protected a network a bit too well. Finally, we shift gears to talk about HYROX, personal discipline, and how renovating your body translates to renovating your business. Key Topics & Highlights:

• The "Red Flag" Sheet: Luke shares the warning signs he looks for before taking on a project, including a lack of process ownership, bad team attitudes, and missing Standard Operating Procedures (SOPs). If a process is broken, automating it just gives you a faster bad process.
• The Simplest Fix with the Biggest Impact: How centralizing multiple disjointed legacy systems into one interface can instantly highlight process flaws and streamline operations.
• AI in Manufacturing (Hype vs. Reality): We separate the buzzwords of the "smart factory" from what actually works. Luke explains that the biggest measurable KPI for AI in the industry today is forecasting—predicting material shortages, customer demands, and supply chain delays.
• An AI Cyber-Security Horror Story: Luke shares a terrifying edge case where an AI system was trusted to protect a business network from a cyber threat. It succeeded... by finding the API keys and deleting all the hard drives and backup volumes so the threat couldn't access them.
• Change Management & Avoiding the "Big Bang": Why the hardest part of software isn't building it, but getting staff to adopt it. Luke explains why building with staff is critical and why a forced "Big Bang" launch (killing the old system overnight with no overlap) often leads to failure.
• HYROX & Business Discipline: Sean and Paul ask Luke about his intense 6-day-a-week HYROX training regimen. The trio discusses how the consistency and discipline required for physical fitness perfectly mirrors what it takes to push a business past the 5-year survival mark.
• The Ultimate Fix: If Luke could walk into any manufacturing business tomorrow and fix just one thing, it would be visibility. You can't manage what you can't measure.

• Yellow Box Software: yellowbox.software (Luke Passmore's company, where listeners can book a virtual coffee or discovery call).
• Contact Luke Directly: You can email Luke at [email protected].
• HYROX: The global fitness racing competition Luke trains for and Sean discusses. (External link: https://hyrox.com/)
• Submit your Admin Nightmares: mailto:[email protected]
• Paul's LinkedIn: https://www.linkedin.com/in/ukwebdevelopment/
• Sean's LinkedIn: https://www.linkedin.com/in/seansale/
• Ctrl+Alt+Dev YouTube Channel: https://www.youtube.com/@ctrlaltdevpodcast
• Ctrl+Alt+Dev Spotify: https://open.spotify.com/show/3NF9wHGBjqTFNowfbBbODc
• Ctrl+Alt+Dev Apple Podcast: https://podcasts.apple.com/us/podcast/ctrl-alt-dev/id1825374857

Welcome to Episode 24 of CTRL-ALT-DEV! Today, we are stepping away from the high-level future-gazing and bringing it right back down to earth with our guest, Luke Passmore of Yellow Box Software. Luke specializes in building bespoke software solutions that turn the chaos of spreadsheets, human memory, and WhatsApp groups into structured, visible operations for SMEs—particularly in the manufacturing and logistics sectors. In Part 1 of this fantastic conversation, we explore the messy reality of implementing tech, why businesses need to stop asking for "shiny apps," and the vital difference between rule-based automation and pattern-based AI. Key Topics & Highlights:

• The Messy Reality of Tech: Why the clean logic of developers doesn't always survive contact with the real world. From bad weather on building sites to humans simply overriding standard procedures, tech has to be designed around the chaos of reality.
• The "Shiny App" Syndrome & "On the Shelf" Software: Luke discusses the common trap of businesses wanting to build an app just to have their logo on a phone screen without understanding the "why". We also talk about "off-the-shelf" software that quickly becomes "on-the-shelf" software because teams refuse to adopt it.
• Are Manufacturing and Engineering Behind? Not necessarily. Luke explains why industries with 250 years of history, complex operations, and tight margins take longer to adapt. It isn't because they are laggards; it's because the stakes (like plant downtime) are incredibly high.
• Where AI Builders (Like Replit) Fall Short: Low-code tools are great for MVPs, but AI completely struggles if a business's data is messy or if there is no Standard Operating Procedure (SOP) mapped out first. You have to define the current state before AI can help you reach the end goal.
• Automation vs. AI: A brilliant definition from Luke: Automation is rule-based (A triggers B), while AI is pattern-based. The secret is to use automation to move the data, and AI to do the heavy lifting and aggregate it.

• Yellow Box Software: yellowbox.software (Luke Passmore's company website, explicitly mentioned by Paul).
• Luke Passmore on LinkedIn: https://www.linkedin.com/in/lukejpassmore/
• Replit: https://replit.com/ (Discussed regarding low-code AI builders and MVPs).
• Mind Studio: https://mindstudio.ai/ (Mentioned alongside Replit as an AI builder tool).
• Sunrise Networking App: https://www.sunrisenetworks.co.uk/
• LinkedIn Profiles: Paul's LinkedIn: https://www.linkedin.com/in/ukwebdevelopment/ Sean's LinkedIn: https://www.linkedin.com/in/seansale/
• Ctrl+Alt+Dev YouTube Channel: https://www.youtube.com/@ctrlaltdevpodcast
• Ctrl+Alt+Dev Spotify: https://open.spotify.com/show/3NF9wHGBjqTFNowfbBbODc
• Ctrl+Alt+Dev Apple Podcast: https://podcasts.apple.com/us/podcast/ctrl-alt-dev/id1825374857

Welcome to Episode 23 of CTRL-ALT-DEV! Today, Sean and Paul tackle the pricing and business model crisis that is quietly terrifying the professional services industry. If AI just compressed your six-week project into 60 seconds, charging by the hour is actively making you poorer. In this brutally honest episode, Paul opens up the Green Gorilla Apps (GGA) playbook to explain why they just slaughtered three sacred cows: timesheets, two-week sprints, and the billable hour. From the pain of their worst quarter to the triumph of their best week ever, this episode is a blueprint for transitioning from hourly billing to value-based outcomes in the AI era. Key Topics & Highlights:

• Listener Question: The Efficiency Trap: Dan from Manchester asks how to handle dropping revenue when his 7-person dev shop uses Claude and Cursor to turn a 300-hour project into 40 hours. The answer? You are the blacksmith charging by the swing of the hammer instead of the horseshoe. Stop selling hours and start selling the solution.
• GGA's Pivot to Outcome Billing: Paul shares a real-world example of taking a financial reconciliation process from a 6-week manual grind to a 60-second automated task. Under the old hourly model, GGA would have billed £7,600. By billing for the £250k value created, they invoiced £85k. The paradox of the old model is that the better and faster you get, the less you earn.
• Workflow Inversion & The 10-80-10 Rule: We revisit the concept that machines now do the heavy 80% of the work, while humans orchestrate the initial 10% (strategy/intent) and the final 10% (review/judgment). Developers are no longer typists; they are highly valuable guardians of the codebase.
• Slaughtering Sprints and Timesheets: Why the traditional two-week sprint is just artificial packaging in 2026. When AI can refactor code in an afternoon, making the work wait for a sprint ceremony is pointless.
• Defending Against Scope Creep: How to rewrite your Statement of Work (SOW) to focus on milestones and strict definitions of "done" (functional tests, business KPIs, and client sign-off) instead of tracking hours. If the client wants new features, it's a new SOW.
• 3 Actionable Takeaways (Do These This Week):
1. Audit your pricing model (cost-plus pricing will kill your margins this year).
2. Map your deliverables to business outcomes (what is it worth to the client?).
3. Rewrite your Statement of Work templates in the language of outcomes, not tasks.
• Tech News Roundup:
• GPT-5.5 Drops: OpenAI's new model ships with proper agentic computer use (scoring 78.7% on OSWorld). It can now operate legacy systems with no APIs—but humans must stay in the loop for high-stakes actions.
• Google Workspace Intelligence: Gemini is now baked into every SMB workspace account by default, indexing Gmail, Docs, Drive, and Sheets. Action item: Audit your tenant settings today to see what HR docs or NDAs are globally indexed!
• Anthropic's Claude Design: A new research preview powered by Claude Opus 4.7 that ingests your code base and design systems to generate prototype slides and one-pagers, raising the floor for competent business visuals.

Join us next week as we tackle the AI adoption gap in mid-sized companies, exploring why 50-developer firms are the ones currently cracking under pressure! Links & Resources Mentioned:

• Submit Your Questions: mailto:[email protected]
• CTRL-ALT-DEV YouTube Channel: Check out the video version of the podcast and join the community in the comments!
• Cursor: https://www.cursor.com/ (The AI code editor mentioned by Dan in the listener question).
• Lovable & Replit: https://lovable.dev/ & https://replit.com/ (Mentioned by Paul as AI builders eating the bottom of the bespoke software market).
• ChatGPT / GPT-5.5: chatgpt.com
• Google Workspace / Gemini: workspace.google.com
• Claude Design (Anthropic): https://www.anthropic.com/claude
• Gamma: https://gamma.app/ (The AI presentation tool Paul mentions is taking a direct hit from Google Slides' new AI features).
• LinkedIn Profiles: Paul's LinkedIn: https://www.linkedin.com/in/ukwebdevelopment/ Sean's LinkedIn: https://www.linkedin.com/in/seansale/
• Ctrl+Alt+Dev YouTube Channel: https://www.youtube.com/@ctrlaltdevpodcast
• Ctrl+Alt+Dev Spotify: https://open.spotify.com/show/3NF9wHGBjqTFNowfbBbODc
• Ctrl+Alt+Dev Apple Podcast: https://podcasts.apple.com/us/podcast/ctrl-alt-dev/id1825374857

Welcome back to Part 2 of our deep dive into Claude Cowork! Building on the use cases from Part 1, Sean shares his real-world results using Cowork for CRM follow-ups and weekly planning. We then pit Cowork against the major alternatives like ChatGPT 5.4, Google Gemini, and open-source frameworks, breaking down the honest strengths and weaknesses of each option for an SMB. We also introduce a new "What We Got Wrong" segment to correct a misconception from last week, and wrap up with a massive news roundup covering GPT-5.4's native computer use, Apple Business going free, and Anthropic's MCP crossing 97 million installs! Key Topics & Highlights:

• Sean's Cowork Update: Sean reveals how he uses Cowork integrated with OpenAI Whisper to dictate CRM updates on the move, bypassing easily ignored notifications. Cowork also caught an overdue client invoice that he missed, paying for his subscription instantly.
• Cowork vs. The Alternatives:
• ChatGPT (with GPT-5.4): Boasts impressive agent capabilities and native computer use, but we question its unsupervised production readiness when handling real business CRM data.
• Google Gemini: Excellent if you live entirely in the native Google Workspace ecosystem, but it currently connects only to web-based services and lacks Cowork's deep local file system access and complex multi-step scheduling.
• Open Source Agents: Great for technical teams with strict data sovereignty needs (like NHS or financial data), but the setup and maintenance overhead is too high for the average professional services firm.
• 3 Actionable Takeaways (Do These This Week):
1. Write down your top three admin time-sinks exactly as if you were briefing a human to do them.
2. Start with just one scheduled task and run it for two full weeks to build trust and calibrate.
3. Audit your repeatable, rule-based digital tasks, if the data is digital, it is a prime Cowork candidate. Bonus: Try the family weekend or meal planner use case first to viscerally feel the time saved!
• What We Got Wrong (The Blank Page Problem): We correct a mistake from Part 1: you don't need a perfectly structured, over-engineered prompt to start. Describe your problem conversationally to the AI and iterate; the worst first prompt is infinitely better than a perfect one you never write.
• Listener Challenge: Email us your worst admin time-sinks at [email protected]. We will pick the best submissions and build the AI workflow to solve them live on our YouTube channel!
• Tech News Roundup:
• GPT-5.4 Native Computer Use: OpenAI's new model can now physically click your mouse and type on your keyboard, scoring 75% on the OSWorld benchmark to beat human experts.
• Apple Business Going Free: Launching April 14th, Apple is offering free MDM and business email with a custom domain, taking a direct shot at Google Workspace. (But don't cancel your current workspace just yet, as the email features require OS versions that don't ship until Autumn 2026!)
• MCP Hits 97 Million Installs: Anthropic's Model Context Protocol is the new "HTTP of AI agents," allowing different software to seamlessly connect without bespoke API builds. It has just been donated to the Agentic AI Foundation under the Linux Foundation to ensure multi-decade infrastructure stability.

Get in touch with the podcast here:

• Submit your Admin Nightmares: mailto:[email protected] Paul's LinkedIn: https://www.linkedin.com/in/ukwebdevelopment/ Sean's LinkedIn: https://www.linkedin.com/in/seansale/
• Ctrl+Alt+Dev YouTube Channel: https://www.youtube.com/@ctrlaltdevpodcast

Links & Resources Mentioned:

• Claude Cowork (by Anthropic): claude.ai
• OpenAI Whisper: https://openai.com/index/whisper/
• ChatGPT / GPT-5.4: chatgpt.com
• Google Gemini: gemini.google.com
• Apple Business: business.apple.com
• Model Context Protocol (MCP): modelcontextprotocol.io
• Agentic AI Foundation (Linux Foundation): www.linuxfoundation.org

Welcome to Episode 22 of CTRL-ALT-DEV! With our recent future-gazing retrospective officially wrapped, we are kicking off a brand-new two-part series focused on deep dives into specific AI tools. No hype, no landing page fluff, just real, in-the-trenches use cases. Today, we are looking at a tool that has fundamentally changed the way we work: Claude Cowork. We explore how to shift your mindset from using AI as a passive "search engine" to employing it as an active background digital PA that autonomously manages your calendar, preps your meetings, and even plans your family's weekly meals. Key Topics & Highlights:

• Listener Question: Is AI Admin Realistic for Small Teams? A professional services founder asks if AI automation is actually feasible without a dedicated ops team. The secret is framing: stop thinking of AI as a tool you have to actively open, and start treating it as a staff member with a very specific, scheduled brief.
• The Paradigm Shift of Claude Cowork: Moving away from traditional chat models where you have to do the "doing". Cowork securely connects to your file system, Google Calendar, Notion, and connected apps via an MCP integration to take consequential actions on your behalf before you even wake up.
• Use Case 1: The Sunday Morning Week Prep: Paul shares how he automated his chaotic Sunday planning ritual. Now, a scheduled task runs while he sleeps, scanning for calendar conflicts, prioritizing tasks, and generating Notion "prequel plans" (meeting agendas and prospect research) for every meeting in the week ahead.
• Use Case 2: The Ultimate Family Meal Planner: How AI saves Paul 39 hours a year and around £4,800 by cross-referencing family calendars, 14 recipe books, and current cupboard inventory (captured in under six minutes via Whisper Flow) to create a budget-friendly weekly meal plan and push the exact ingredients to the "Bring!" digital shopping list app.
• Use Case 3: The Daily Briefing: Waking up at 6:55 AM to a prioritized list of "rocks, pebbles, and sand," complete with deep-dive research into the prospects you are meeting that day, giving you a massive commercial advantage over competitors who are still winging it.
• Use Case 4: The Overdue Task Scanner: An automated Thursday afternoon scanner that flags overdue items in your project management system, providing an action brief on the dependencies and what needs to happen to rescue the deadlines.
• Use Case 5: Friday 4 PM Audits: Removing self-deception with an automated Friday audit that brutally but honestly tells you what you actually completed versus what you planned.
• Use Case 6: Family Weekend Logistics: Curing Sunday morning decision fatigue by having AI scan the weather, family calendars, and your existing discount memberships (like National Trust and O2 Priority) to plan the perfect, low-cost family weekend out.
• The 4 Risks of Automation: An honest look at the dangers of setting and forgetting AI, including data governance and security, the need for human verification, the risk of automating genuine human connection, and system dependency.

(Note: We had so much to cover that we split this tool deep-dive into two parts! Join us next time for Part 2, where we compare Cowork to the alternatives and dive into the latest AI news).

Connect with Paul & Sean

Paul Rhodes - [email protected]

https://www.linkedin.com/in/ukwebdevelopment/

Sean Sale - [email protected]

https://www.linkedin.com/in/seansale/

Resources:

Claude - https://claude.ai/new

Notion - https://www.notion.com/en-gb

Bring! App - https://web.getbring.com/login

Welcome back to the continuation of our journey into 2036!

Sean and Paul finish their massive deep dive into the sci-fi future of work, life, and society. From Amazon "stress-testing the future of work" by replacing thousands of developer hours with AI, to the uncomfortable realities of frictionless AI companionship, this episode leaves no stone unturned. Plus, the hosts wrap up with a massive segment on how AI data centers, digital twins, and automated officiating will fundamentally revolutionize the beautiful game of football. Key Topics & Highlights:

• Amazon's Blueprint for the Future: Why Amazon isn't just cost-cutting, but completely redesigning how work actually happens. The hosts discuss the staggering reality of Amazon Q saving 4,500 "developer years" and the danger of AI "eating the career ladder" so juniors can no longer become seniors, putting vital tribal knowledge at risk.
• Rapid-Fire 2036 Predictions: Plausible or not? Paul and Sean debate what will be normal in 10 years, including permanent AI tutors, drone corridors, robot-assisted elderly care, biometric payments, and a new societal inequality between those who control AI and those who are controlled by it.
• AI Companionship & Intimacy: As AI and robotics become more advanced, will people choose frictionless, predictable machine intimacy over the messy, necessary friction of real human relationships?. The hosts discuss the trade-offs between curing elderly loneliness and outsourcing genuine human connection.
• The Future of Football: How AI will shift football from being reactive to highly predictive. Sean and Paul explore using digital twins to test tactics, predicting player injuries by analyzing tackle velocity, and how even lower-league clubs could scout global talent via AI agents while sitting on a train.
• Fixing VAR: Sean and Paul vent their frustrations with current football officiating (like wrestling in the penalty box) and discuss how automated offsides, AI ball-tracking, and wearable tech could remove human error and instantly resolve decisions on corners and handballs.

The Ultimate Question: The future isn't man versus machine; it is about what kind of society humans decide to build around the machine, and what we refuse to hand over. Resources & Media Mentioned:

• Back to the Future (Film): Referenced regarding skipping roads for the sky.
• Demolition Man (Film): Brought up during the discussion on frictionless human vs. machine companionship.
• Wrexham AFC: Mentioned as an example of building a team for a journey rather than just flipping players for profit.

Tell us what we got right, what is complete nonsense, and what we completely missed about 2036 by reaching out here:

Paul Rhodes - [email protected]

https://www.linkedin.com/in/ukwebdevelopment/

Sean Sale - [email protected]

https://www.linkedin.com/in/seansale/