- 155
- Episodes
- 19
- Ratings
- Weekly
- Cadence
- 2017
- First episode
About ProductivityCast
The show about all things personal productivity
- Publisher
- Ray Sidney-Smith
- Category
- education · society & culture · technology
- Language
- en
- Explicit
- No
- First episode
- 8 Jul 2017
- Latest episode
- 28 Sept 2026
Latest episodes
155 episodes in the feed.
28 Sept 2026
The AI Coding Companion: Vibe Coding Your Bespoke Productivity Universe
This week, we continue swimming in the river of AI within our series, The AI-Powered Professional. Today, we are exploring Vibe Coding. We discuss the next major leap in personal productivity: using AI to help you build the bespoke tools, workflows, and interfaces your work actually requires. This opportunity is now available not only to professional developers, but also to non-coders and power users who can think clearly, describe what they want, and iteratively direct AI toward a useful result. (If you’re reading this in a podcast directory/app, please visit https://productivitycast.net/155 for clickable links and the full show notes and transcript of this cast.) Enjoy! Give us feedback! And, thanks for listening! If you'd like to continue discussing The AI Coding Companion: Vibe Coding Your Bespoke Productivity Universe from this episode, please click here to leave a comment down below (this jumps you to the bottom of the post). In this Cast | The AI Coding Companion: Vibe Coding Your Bespoke Productivity Universe Ray Sidney-Smith Augusto Pinaud Art Gelwicks Francis Wade Show Notes | The AI Coding Companion: Vibe Coding Your Bespoke Productivity Universe Resources we mention, including links to them, will be provided here. Please listen to the episode for context. Lemmings Lemming Suicide Myth Disney Film Faked Bogus Behavior Raw Text Transcript Raw, unedited and machine-produced text transcript so there may be substantial errors, but you can search for specific points in the episode to jump to, or to reference back to at a later date and time, by keywords or key phrases. The time coding is mm:ss (e.g., 0:04 starts at 4 seconds into the cast’s audio). Read More Voiceover | 00:00Are you ready to manage your work and personal world better to live a more fulfilling, productivelife? Then you've come to the right place. Welcome to ProductivityCast, the weekly show aboutall things personal productivity. Here are your hosts, Ray Sidney Smith and Augusto Pinaud withFrancis Wade and Art Gelwicks.Ray Sidney-Smith | 00:17Welcome back, everybody, to ProductivityCast, the weekly show about all things personalproductivity. I'm Ray Sidney Smith.Augusto Pinaud | 00:24I'm Augusto Pinaud.Francis Wade | 00:26I'm Francis Wade.Art Gelwicks | 00:28And I'm Art Gelwicks.Ray Sidney-Smith | 00:29Welcome, gentlemen, and welcome to our listeners to this episode. Today, we are going tocontinue swimming in the river of AI with our series, The AI-Powered Professional. And today,specifically, we're exploring vibe coding. We're going to discuss really the next major leap inpersonal productivity, I think, which is using AI to help you build bespoke tools, workflows, andinterfaces your work actually requires. This is an opportunity now for us to available not only toprofessional developers, but to the rest of us, to non-coders and power users who can thinkclearly, describe what they want, and iteratively direct AI toward a useful result. Let's first talkabout what vibe coding is, and then we can get into really just three paradigms, three personasthat I've developed for us to bulk together our discussion for today. And so who wants todescribe what they think vibe coding is and or ask any questions about what vibe coding is?And then we can move on from there.Francis Wade | 01:35Nominated.Art Gelwicks | 01:37Yeah, you go ahead. You set up.Ray Sidney-Smith | 01:40Let's start with vibe coding having no official definition. There are going to be people who definevibe coding very differently. Vibe coding, from my perspective, is a way for folks to use somekind of artificial intelligence to support their software development practice. Now again, this isone of those cases where software development is a very broad term for what we're doing here.Just so that everyone is aware, this term was coined in 2023 by Andrei Karpathy. AndreiKarpathy is one of the co-founders of OpenAI—he worked on their deep learning and computervision—and then later joined Anthropic here in 2026. Be that as it may, he coined the term "vibecoding", and the way in which he describes it is as a form of coding where you can "fully give into the vibes, embrace exponentials, and forget that the code even exists."This is basically a way of not writing code manually. That means it's a very broad definition andgives way to a whole bunch of potentiality because now you're using your cognitive effort andnatural language in order to come up with code. Generative AI models today speak code andhave been trained on so much code that it's very easy for them to build software in certain ways.We can use those capabilities to our own best effort.Art Gelwicks | 03:33This whole episode, I'm going to be up on my soapbox about certain things because comingfrom old-school code writing decades ago, this to me screams of—for lack of a betterterm—executive coding. Being able to say: "Just do the thing, and I'll look at the thing that youdid and tell you how it's not right, and then you can do it again."There's no structure, no thought process involved, no ramifications or planning. It removes allthe logical friction necessary to provide something substantive and supportive. That's exactlywhat's desired right now: to eliminate those things and not have to go through that routine andrigmarole. You want to be able to just say, "Make it." That's great if you trust the thing that ismaking it to do so in a way that is sustainable, supportive, and reliable.Ray Sidney-Smith | 04:32I argue for the exact opposite, which is that this is about applying cognitive effort to solve smallproductivity problems in your ecosystem, not attempting to replace professional softwaredevelopers. I think it would be very foolish to think this is going to replace a software developer.This is about enabling software developers, and for non-coders, enabling us to infuse code intoour world where limitations previously existed.Let me define three personas for today's discussion: The Designer: These are non-coders. Your main skill is describing what you want withprecision to define the shape and function of lightweight tools or scripts (e.g., GoogleApps Script or Excel macros). The Integrator: Power users who understand configuration files (CSVs, JSON, XML) andcan connect tools together to accelerate custom workflows. The Developer: Professional software engineers using AI companions to refactor, review,and generate code while focusing on architecture and quality.With that, let's talk about the non-coder level and what they can achieve with AI.Francis Wade | 08:35I think the world of the non-coder is the one that's changed the most. All of a sudden anyonecan code, which means anyone can imagine solutions. Even if they aren't fully successfulinitially, getting people to think in terms of software, automation, and coded solutions at a smallpersonal level is huge.You don't need to take a college course or pass an exam. The learning curve isn't as steepanymore, so you can start playing around right away to solve daily problems or present smallincremental answers to clients or managers. That capability feels like having a virtual softwarefirm at your fingertips.Ray Sidney-Smith | 10:41Francis Wade | 10:45It's incredible to have that kind of power at your fingertips. We are in a shift that will change howpeople approach their work.Ray Sidney-Smith | 11:13I would say we are in a technological evolution. Over the past 20 years, we've reached aninflection point where natural language interfaces allow us to communicate intent directly tocomputing systems.However, non-coders must be cautious. Large language models are probabilistic,non-deterministic software. Math and precision require deterministic software (like accountingtools). The goal for the non-coder is to learn basic programming principles—inputs, outputs,logical branching, and structured formats like Markdown—so you can craft precise instructionsand think through your workflow logic clearly.Art Gelwicks | 15:10Here's the insidious part: this group stands to reap the greatest benefit, but also faces thegreatest risk. AI tools are marketed with the promise that "you don't have to know anything, justtell it what to do."Take Excel formulas as an example. An AI can generate complex formulas, but if you don'tknow enough to verify the output, you risk relying on incorrect calculations. You have to treat AIlike delegating to a human assistant—you need checks and balances to verify that what wasbuilt actually matches your requirements.Augusto Pinaud | 17:31It reminds me of when teachers told us in school that we wouldn't always have a calculator inour pocket. It wasn't about the tool itself, but understanding how to verify the result. We need topay close attention to output quality, whether it's checking drafted communications or verifyingreferences, to ensure AI hasn't hallucinated plausible-sounding facts.Francis Wade | 19:27That highlights the need for user judgment. AI gives us incredible technical capability, but lacksdomain judgment. When non-coders jump straight into building complex systems withouttechnical guidance or experienced oversight, they risk creating unmaintainable setups becausethe tool won't stop them from making poor architectural choices.Art Gelwicks | 22:17Exactly. Many vibe coders haven't experienced major system failures or database corruption, sothey don't know what a mess looks like. When something breaks, asking the AI to fix it mightintroduce new bugs if there isn't a structured review and rollback plan.Francis Wade | 23:22Some people prompt AI to act as its own reviewer by asking it to double-check work againstguidelines or software standards. Having multi-agent setups or explicit review steps helps addthat necessary layer of verification....
25 Sept 2026
AI in Everything: Maximizing AI Within Your Existing Platforms and Tools Part Two
In this week's episode, the ProductivityCast team continues their conversations about how AI is embedded across many of the tools that we currently use and how to integrate them into the places we already work. (If you’re reading this in a podcast directory/app, please visit https://productivitycast.net/154 for clickable links and the full show notes and transcript of this cast.) Enjoy! Give us feedback! And, thanks for listening! If you'd like to continue discussing AI in Everything: Maximizing AI Within Your Existing Platforms and Tools Part Two from this episode, please click here to leave a comment down below (this jumps you to the bottom of the post). In this Cast | AI in Everything: Maximizing AI Within Your Existing Platforms and Tools Part Two Ray Sidney-Smith Augusto Pinaud Art Gelwicks Francis Wade Show Notes | AI in Everything: Maximizing AI Within Your Existing Platforms and Tools Part Two Resources we mention, including links to them, will be provided here. Please listen to the episode for context. AI Models, Assistants & Specialized Tools Gemini (Google) CoPilot (Microsoft) ChatGPT Claude NotebookLM (now Gemini Notebook) Evernote AI Assistant Productivity, Office & Note-Taking Software Google Workspace Google Drive Google Sheets Google Docs Microsoft 365 / Microsoft Office suite Microsoft Excel Microsoft Word Microsoft Outlook Clipchamp Capacities Evernote Search Engines & Historical Web Tools Google AskJeeves Wayback Machine Publications, Media & Platforms CliffsNotes Raw Text Transcript Raw, unedited and machine-produced text transcript so there may be substantial errors, but you can search for specific points in the episode to jump to, or to reference back to at a later date and time, by keywords or key phrases. The time coding is mm:ss (e.g., 0:04 starts at 4 seconds into the cast’s audio). Read More Ray Sidney Smith | 00:00 Are you ready to manage your work and personal world better to live a more fulfilling, productive life? Then you've come to the right place. Welcome to ProductivityCast, the weekly show about all things personal productivity. Here are your hosts, Ray Sidney-Smith and Augusto Pinaud with Francis Wade and Art Gelwicks. Ray Sidney Smith | 00:17 Welcome back, everybody, to ProductivityCast, the weekly show about all things personal productivity. I'm Ray Sidney-Smith. Francis Wade | 00:24 I'm Francis Wade. Art Gelwix | 00:26 And I'm Art Gelwicks. Ray Sidney Smith | 00:27 Welcome, gentlemen. Welcome to our listeners and onward with this episode from our last episode where we were talking about basically how AI is being embedded in all of the tools that we currently use. It is becoming... Somewhat of a commodity feature in many of the tools. And I think that there's a value to that. And so we're talking through what that really means and what So at this point in our discussion, I want us to turn our sights on the more practical ways in which we can use these embedded tools. So that we can actually figure out where in our productivity stacks the tools can be most helpful. And I always think about it from really the simplest of things, right? And journey of a thousand miles begins with the first step, right? And I think that most people want to change the world with AI. And I just want to send the next email. And so I just really want it to do very simple things to augment my life. As I frequently say now to audiences, technology is there to empower human endeavors. It should always and forever be a tool to empower human endeavors. And so I don't need AI to live my life. I need it to augment my life in these little small ways that help my life be better and the lives of people around me. So let's talk through this. What are those ways in which you've implemented AI inside of your embedded work? AI tools within maybe Gemini and Google Workspace or within another tool or Copilot within Microsoft 365 or even ChatGPT or Cloud, which connects to many of the Microsoft products? Art Gelwix | 02:16 I'll start with a couple of examples. The application of AI within our, what I want to say, our daily driver apps is I think has caused some consternation for a lot of people because It's like this is a new feature, but I don't know what to do with it. I don't know how to derive a value. I've approached it from the standpoint of start with what you're doing already, which is looking for information and synthesizing information. You need to use it to leverage the information that you already have that you know is sound, sane, and... Validated So for example, within Copilot, within Microsoft space, if you're licensed for that, you can use it looking at your document assets. You can use it within things like Excel to generate new formula structures, things that you're already familiar with. Within capacity, the tool I use all the time. Being able to generate a chat around a topic that creates the note base that I validate that extends on the thinking around a topic that I've been working on, which integrates then into scheduled planned activities that I need to pursue. Why is that so critical? One, because you're doing something that you are comfortable to do. But verify what the AI system in that tool is giving you back. You're just not taking it at its face value. You look at it and you go, yeah, that's not right. Or yeah, that's really good. The second part is to look at it as search 2.0, to be able to go past that initial search prompt to say, hey, find me this stuff. But then get into it further. What else about this thing? Tell me more about this thing. Let's expand on that a little bit further. Getting comfortable with that process in the tools that we already use is a safe space to do it. Because again, we're familiar with what the end result should be. If we start to get familiar with that in just generic open spaces... We're not entirely sure what the result is, so we either have to take it at face value, Or we have to kind of doubt how things are coming back, have that constant question. I think back to the early days of, say, Google or Ask Jeeves, if you really want to go back into the Wayback Machine, is a great example of that. When they first started entering into the world of natural language questions, that was just earth-shaking. Everybody thought this was the coolest thing ever. I didn't have to put in keywords and connector parameters and ands or ors. I could just We just have the ability to ask more questions. We have the ability to have personas and structures that look at things a specific way. But starting from an application that you already know, When you look at the result that comes back, you can go yeah, it did look at it the right way, or I need to tune it a little bit better, or I need to adjust accordingly. Ray Sidney Smith | 05:20 I found myself going into Google Drive and now having these conversations with the files in Google Drive. And it's actually quite helpful to have that embedded conversational component that is very different than doing an advanced operation search, right? And I know all of the advanced operators in Google Drive, at least the ones that are publicly known to folks. And I use them very effectively to find things. But it's been really helpful to have a fuzzy search approach when I know that file is in there, I just don't remember X or Y about it and be able to just natural language ask for it is helpful. And then the other side is when you want to be able to say, "Okay, everything in this folder I want to talk about everything in this folder in kind of the same way you would with Notebook LM, which is a little bit more grounded in the data. Now you are similarly grounded in the data that is already in your system. So you didn't have to go to Notebook LM and add each individual file. They're just there and you're able to go ahead and engage with it. So it's really powerful. Francis Wade | 06:27 There's a mindset shift there. I believe is coming, which is away from changes being driven by what's available as opposed to what's needed. I'm riffing off of what Art said. But he said, you got to start with what we are doing already. And I think we should almost be skeptical or stingy about a new possible change, let's put it that way. Simply because partly because there's more changes that are being suggested to us that are being advertised to us than we can possibly implement in a lifetime. So this is not going to get better, it's going to get worse. Decide to play the odds and say, you know what, I can't implement all of the embedded AI options that are available in my I don't have enough lifetime to do it. And the question is, do you experiment until you find something or do you take? שעוד פרק, שזה I'm not taking any suggestions whatsoever, which is a bit. Draconian, but... I'm going to look for the one or two changes that are going to move the needle the most in my productivity. Which would mean that I need to have an understanding of the bottlenecks to my productivity and focus my efforts on them. Believing that if I "Focus on the few." they'll move the needle the most, that there's some Pareto effect in here somewhere. And I somehow believe that our future is going to be Less raw experimentation and more diagnosis, analysis and targeted searching. And again, partly it's because We're going to have to say way more no's than yes's to suggestions that we include an embedded AI in our productivity stack. We're going to... 99% of the time, we're going to, we got to say no. We got to, but the question is. Where do you get the Pareto effect from the 1% and how do you find the 1%? How do you find a few things that are going to make you 10 I believe that there'
18 Sept 2026
AI in Everything: Maximizing AI Within Your Existing Platforms and Tools
This week, we continue our dive into the world of Artificial Intelligence with another episode in our series, The AI-Powered Professional. Today, we are exploring AI in Everything, focusing on the shift of AI from being a standalone tool to becoming a core, embedded capability within the software we use every day, making AI truly everywhere. The biggest productivity gains are coming from smarter versions of the platforms we already rely on, rather than from brand-new tools. (If you’re reading this in a podcast directory/app, please visit https://productivitycast.net/153 for clickable links and the full show notes and transcript of this cast.) Enjoy! Give us feedback! And, thanks for listening! If you'd like to continue discussing AI in Everything (The Integration of AI: Maximizing AI Within Your Existing Platforms and Tools) from this episode, please click here to leave a comment down below (this jumps you to the bottom of the post). In this Cast | AI in Everything (The Integration of AI: Maximizing AI Within Your Existing Platforms and Tools) Ray Sidney-Smith Augusto Pinaud Art Gelwicks Francis Wade Show Notes | AI in Everything (The Integration of AI: Maximizing AI Within Your Existing Platforms and Tools) Resources we mention, including links to them, will be provided here. Please listen to the episode for context. Microsoft 365 Google WorkspaceTodoist Extended mind, Opinionated Raw Text Transcript Raw, unedited and machine-produced text transcript so there may be substantial errors, but you can search for specific points in the episode to jump to, or to reference back to at a later date and time, by keywords or key phrases. The time coding is mm:ss (e.g., 0:04 starts at 4 seconds into the cast’s audio). Read More Voiceover | 00:00 Are you ready to manage your work and personal world better to live a more fulfilling, productive life? Then you've come to the right place. Welcome to ProductivityCast, the weekly show about all things personal productivity. Here are your hosts, Ray Sidney Smith and Augusto Pinaud with Francis Wade and Art Gelwix. Ray Sidney Smith | 00:18 Welcome back, everybody, to ProductivityCast, the weekly show about all things personal productivity. I'm Ray Sidney Smith. Augusto Pinaud | 00:25 And I'm Augusto Pinaud. Francis Wade | 00:26 I'm Francis Wade. Art Gelwix | 00:28 And I'm Art Gelwix. Ray Sidney Smith | 00:29 Welcome, gentlemen, and welcome to our listeners to today's episode, where we are going to be continuing on in our AI-powered professional series. Today we're going to be exploring AI in everything, basically focusing in on the shift of AI from being a standalone tool—which we mostly have today—to becoming more of a core or embedded capability within software we use every day, making AI everywhere. We're seeing that happening in the market as well. Art Gelwix | 01:49 I would say the biggest impact that I see right away is within my note-taking applications. I've seen—especially in the web-based ones—a direct integration of AI at the base level within the application, primarily because it has your information there to leverage and to be able to run through its models. Augusto Pinaud | 02:31 I would say the same: the notes and the knowledge base. All those things that I have collected and refer to regularly, having the AI there has been really fantastic. Francis Wade | 03:57 The biggest impact for me has been on my writing. Not so much in the tools I used to use, because I switched—I'm no longer using the tools I used to use; I'm using new tools. The improvements for me have not been within the existing apps; they've been in entirely new capabilities. Ray Sidney Smith | 04:51 I'll say that the first place I saw AI really put into my own productivity stack was in email, specifically within the Gmail interface in Google Workspace. That's my primary email, although I have accounts across almost every major email system because I test them for work. The change in my workflow was remarkable. Francis Wade | 08:36 I'm seeing a new way of managing working memory. Supposedly, we can only keep seven or eight items in memory at a particular time. If I'm doing research for an article, for example, I can scan sources, but once I get above eight sources, I'm not very good at keeping them all in play. I end up using the ones I remember most recently, rather than remembering 20, 30, or 40 sources. Ray Sidney Smith | 12:46 It's akin to asking, "Did you use spell check or grammar check in your Word document?" That's the equivalent—it's silly. Francis Wade | 12:54 It's the exact equivalent. Years ago, people asked if you used Grammarly or said you weren't supposed to use it for class. Now we don't even think about it. I believe this is where AI is going. It's a question of skillfully manipulating your tools to expand your capabilities. Ray Sidney Smith | 13:18 Augusto, then Art—go for it. Augusto Pinaud | 13:22 That is exactly what makes it powerful. I've been a heavy journaler all my life, but now some of that has shifted to AI. This weekend, I was working on a new book coming out and working through some stuff with AI. It gave me something where I was unsure, so I asked another chat to give me a summary of all the discussions we'd had on this topic so I could feed it to an AI agent. That process took 30 seconds. In the past, that would have taken a significant amount of time to review and rethink everything. Art Gelwix | 16:21 I love this idea of the AI intern because it provides a clear perspective on its role within your tools. In note-taking, if you expect AI to be an expert generating perfect solutions on everything, you'll be disappointed. But if you treat it like an intern—asking it to pull action items from meeting notes with reasonable expectations—it will be 80-90% accurate based on the context and training you've provided. Ray Sidney Smith | 18:10 Augusto, go ahead. Augusto Pinaud | 18:11 Exactly. We are all leveraging years of accumulated context rather than just installing a raw tool and expecting magic. For instance, I was writing the other day, and the AI pointed out where a statement contradicted something I wrote years ago. When I checked, I realized the old context assumed cell phones without data plans, whereas today everyone is connected. That prompt forced me to update my thinking and improve the article. Ray Sidney Smith | 20:58 When we talk about working inside an ecosystem, there are key advantages for corporate and enterprise environments—namely security, permission controls, and privacy boundaries. These environments keep data much safer than external, unmanaged tools. Art Gelwix | 23:08 I agree completely. AI works best for everyday users when it's invisible—like the underlying search and feature enhancements Google brings to Gemini. It should be a powerful feature within a tool rather than the main attraction. Ray Sidney Smith | 24:52 Augusto? Augusto Pinaud | 24:53 Apple's strategy lets others take early risks while they refine how AI integrates for non-technical users. Eventually, native integrations will leverage on-device context to automate everyday tasks smoothly behind the scenes. Ray Sidney Smith | 26:04 Apple is primarily a hardware and services company, so their timeline and incentives differ from software-first platforms like Microsoft or Google. They can afford to take a measured approach to embedding AI across their hardware ecosystems. Francis, go ahead. Francis Wade | 27:03 For the majority of users, background integration will be fine. But for those looking to optimize, we currently lack a structured framework for identifying exactly where AI can improve a workflow. Right now, it's mostly trial and error. Art Gelwix | 29:46 Building on that, working with AI requires learning its strengths and communication style, similar to onboarding a new team member. Problems arise when people expect AI to conform rigidly to flawed organizational processes without adjusting how they prompt or guide it. Ray Sidney Smith | 31:37 To wrap up this segment, embedded AI in major ecosystems like Google Workspace or Microsoft 365 offers two main benefits: reducing context switching to prevent decision fatigue, and enabling automated cross-tool workflows through standards like the Model Context Protocol (MCP). Ray Sidney Smith | 31:43 MCP acts as a universal open standard connecting different AI models securely to external data sources. It ensures controlled, deterministic outputs while allowing applications to communicate safely across systems. By connecting models and automation tools like Zapier, teams maintain quality control over outputs while linking spreadsheets, email, and notes fluidly. We'll pause here and continue discussing practical applications of embedded AI in our next episode. Ray Sidney Smith | 36:36 While we are at the end of our discussion, the conversation doesn't stop here. If you have a question or comment about what we've discussed, please visit our episode page at productivitycast.net. Feel free to leave a comment or question at the bottom of the page; we read and respond to them there. Voiceover | 38:54 That's it for this episode of ProductivityCast, the weekly show about all things personal productivity, with your hosts Ray Sidney Smith and Augusto Pinaud, with Francis Wade and Art Gelwix. Download a PDF of raw, text transcript of the interview here.
Reach and audience
Public platform figures. Ratings count people who left a rating, not total listeners.
- Apple Podcasts (US)
- 4.9 / 5
- 15 ratings
- Spotify
- 4.5 / 5
- 4 ratings
Contact ProductivityCast
- Guest appearances
- Does not typically book guests
Based on episode analysis; this does not confirm that the show is currently accepting guests.
Host of ProductivityCast?
Claim your podcast to manage its listing and keep your show details accurate.
Pod Engine is an independent podcast discovery and analytics service and is not affiliated with or endorsed by this podcast. Artwork and show content belong to their owners. Full legal notice.
Explore this show
Podcast research with Pod Engine