AI for Business Podcast

In this live demo session from the AI for Business event, Brian builds a complete, working app from a single plain-English sentence, with no coding, no tricks, and no prior Lovable experience assumed. He starts by walking through his own free resource, a 40-plus chapter prompt book and playbook available at Brian's Gift, before diving into a real-time build of a home staging app that lets real estate agents upload a photo of an empty room and generate a fully staged version for their listings. Brian treats this as a deliberately bare-bones demonstration: no advanced prompting techniques, just describing the idea in plain language and answering a handful of follow-up questions Lovable asks automatically. He also shows off the design-inspiration tools in his stack, Dribbble for style ideas and GoFullPage for capturing entire websites in one screenshot, and highlights that both Gemini and ChatGPT are already built into Lovable at no extra cost, giving access to Google's Nano Banana image generation without needing a separate API.   Timeline Summary [0:01] Brian introduces his newly updated prompt book with over 40 chapters [0:49] Where to find it: Brian's Gift, plus a Claude referral link and a Lovable credit bonus link [1:29] Introducing the app builder playbook and the exact build system Brian uses [1:52] The core toolkit: Lovable, Claude, a free GitHub account, the playbook, and a knowledge file [2:17] Dribbble as a free design inspiration site you can feed directly into Lovable [2:55] GoFullPage, a free Chrome extension for capturing an entire website in one screenshot [3:16] The first prompt in the playbook, ready to copy and paste to get started [3:51] Starting the live demo with the simplest possible approach: plain English, no tricks [4:13] Confirming Gemini and ChatGPT are built into Lovable at no extra cost, unlocking Nano Banana image generation [4:54] Introducing the example: an AI home staging app for real estate listings [5:14] Why staging is a strong example: it costs thousands of dollars and many AI alternatives charge per photo [5:51] Writing the very first prompt live, describing the staging app in plain language [7:42] Lovable's automatic follow-up questions: room types, number of design themes, and visual style [9:22] Choosing to require sign-in and submitting the final build request [9:43] What to do if something doesn't work right away: just tell it and let it fix itself [10:29] Watching Lovable generate the build plan and approving it live [11:18] Lovable automatically enabling cloud and database features without manual setup [11:40] Brian's personal take on Google's long-term position in the AI race [12:19] Why the Nano Banana image generator was the turning point for Google's user growth   5 Key Takeaways You Can Build a Working App From One Plain Sentence — Brian's entire opening prompt for the staging app was a single, plainly worded description of the idea. No technical language, no advanced prompting technique, just a clear explanation of what the app should do. Let the Platform Ask the Follow-Up Questions — After a simple first prompt, Lovable automatically asks the clarifying questions needed to complete the build, like room types and visual style, removing the need to think through every detail up front. Built-In AI Models Remove a Whole Setup Step — Because ChatGPT and Gemini are already integrated into Lovable, there's no API to configure or account to connect, which also unlocks Google's Nano Banana image generation at no extra cost. Bugs Are Normal, and the Fix Is Simple — When a built app doesn't work as expected, the fix is often as simple as telling the AI exactly what's wrong and letting it correct itself, rather than treating it as a sign something went irreparably wrong. Design Inspiration Doesn't Have to Come From Your Own Niche — Sites like Dribbble let you pull in a look and feel from a completely unrelated industry and have Lovable build toward that aesthetic, rather than starting from a blank page.   Enjoyed This Episode? If watching a working app get built from a single sentence made this feel a lot less intimidating than you thought, that's the point, just describe the idea in plain English and let the platform guide you the rest of the way. Share this episode with someone who's been putting off building their first app because they think they need to learn to code first, and if it helped, hit subscribe and pass it along to a friend or colleague.  

In this live demo session from the AI for Business event, the same team member behind Revven pulls back the curtain on two much bigger builds: Core Real Elite, an autonomous real estate investing platform, and Homes Daily, a consumer-facing home-selling platform positioned as a direct challenger to sites like Zillow. Both were built primarily using Lovable, stitched together with outside data partnerships for the pieces Lovable's built-in AI can't reach on its own. Core Real Elite is designed to work as a fully autonomous acquisitions system: an "AI Scan" feature that uses Google Street View imagery to spot distressed properties at scale, cross-referenced against public records for foreclosure, probate, and tax delinquency signals, then automatically matched against a database of active buyers, sending offers, contracts, and DocuSign signatures without a human needing to touch any of it unless they choose to step in. Homes Daily flips the same buyer-matching engine around for homeowners, showing sellers exactly which buyers in the system are ready to close on their specific property. The back half of the session gets into the harder, less glamorous parts of building something like this: the real cost of licensing raw data instead of a cheaper API, the legal and compliance guardrails needed to avoid AI practicing real estate without a license, and a monetization strategy built around letting established trainers and influencers white-label the platform to their own audiences instead of selling it directly. The speaker also shares a comparison that sums up the whole session: a tool that took another developer three years and six figures to build was recreated as a working first version in just four weeks.   Timeline Summary [0:01] Introducing Core Real Elite and the vision of wiring separate real estate tools into one autonomous system [0:47] The Intel report feature: finding top zip codes by cash buyer activity and launching campaigns instantly [1:46] The search and buy box feature, similar to Zillow or Redfin but built for investors [2:03] AI Scan explained: using Google Street View to spot distressed properties in minutes [2:49] Cross-referencing property condition with public records for foreclosure, probate, and tax data [4:10] Automatically matching a distressed property against active buyers already in the system [4:29] The fully autonomous pipeline: scanning listings, scraping Facebook and Craigslist, and making offers automatically [5:29] Built-in DocuSign, contract tracking, and automatically notifying title companies and lenders [6:30] Marketing an accepted deal to matched buyers and moving a showing through to close [7:14] Additional tools in the system: an acquisitions agent, deal calculators, and market analysis [7:42] Introducing Homes Daily, the consumer-facing platform for matching sellers directly to buyers [9:08] Why building this without traditional coding knowledge still produced something industry-disrupting [9:51] Housing every seller communication, across call, text, and email, in one unified hub [10:11] The AI call-listening and real-time coaching feature for sales reps [11:11] The white-label monetization strategy: letting trainers and influencers sell it to their own list [12:16] A look at the deal analysis tool and its automatic offer and creative finance suggestions [13:19] Why raw data costs multiple six figures a year, and why an API wasn't a viable option here [14:31] BatchLeads as a more affordable API option for simpler builds [14:56] The honest reality of protecting an idea in an age where AI can rebuild almost anything [15:40] Positioning Homes Daily against Zillow, and catching an overly bold AI-suggested headline [16:48] The compliance guardrails: disclosures, an attorney review, and not letting AI give licensed advice [18:06] Monetizing through paid agent placements while still serving for-sale-by-owner sellers directly [19:41] Confirming the data partnership was finalized that same day, unlocking the next build phase [20:44] Why Lovable alone can't access proprietary data like Zillow's or the MLS without a separate API [22:36] Introducing Ava, the AI assistant built contextually into every page of the platform [23:21] Personal builds for fun: an app for a son's Minecraft interest and a princess dress-up app for a daughter [24:22] The comparison that sums it all up: three years and six figures versus a four week MVP   5 Key Takeaways Autonomous Doesn't Mean Hands Off Forever — Every stage of the system, from scanning for leads to sending offers to closing deals, can be set to fully automated or fully manual, letting the user choose exactly how involved they want to be at each step. Data Costs More Than the Build Itself — For simple apps, tools like ChatGPT or Gemini's built-in capabilities are enough. The moment you need proprietary data, like MLS or Zillow-level information, you're looking at a real data licensing cost that can run into six figures a year. Compliance Has to Be Built In From the Start — Anything that touches real estate advice needs deliberate guardrails to avoid AI practicing without a license, plus clear disclosures and legal review, especially when the tool is designed to directly compete with large, protected platforms. You Don't Have to Sell Your Product to Profit From It — Rather than selling a finished platform outright, letting established trainers or influencers white-label it to their own audience for a revenue share can create profit far faster than direct sales ever would. Speed Is the Real Disruption — A tool that took a traditional developer three years and six figures to build was recreated as a working first version in about four weeks using AI-assisted development, a gap in speed that's reshaping what "moving fast" actually means in this industry.   Enjoyed This Episode? If this demo made you rethink what's possible to build without a developer, start by naming one repetitive task in your own business that a scan, a match, or an automated follow-up could solve. Share this episode with someone still paying a developer six figures for something that might now take weeks, and if it helped, hit subscribe and pass it along to a friend or colleague.  

In this live workshop session from the AI for Business event, team member Mike shows off a sales coaching and training platform he built entirely on his own, with zero coding experience, after seeing a similar tool Brian had put together. What started as curiosity turned into an all-night build session, roughly 150 prompts and sixteen planned phases, using Lovable to build the app and Perplexity Comet as an AI agent that could take his ideas, write the prompts, and execute the build in Lovable largely on its own. The app itself is built for sales teams and covers a lot of ground: a command center tracking calls and appointments, a role-play arena where reps practice against an AI voice trained to simulate different sales scenarios and then grades their performance, an intelligence dashboard tracking conversion trends and best calling times, an objection-handling library, leaderboards, a training academy for onboarding new hires, and a manager's coaching console. Brian and Mike also touch on the bigger lesson underneath the demo: treating AI less like a search engine and more like a collaborator you talk back and forth with until it surfaces ideas you wouldn't have thought of yourself.   Timeline Summary [0:01] When you actually need to bring in a developer, and why it's often much later than people think [1:29] Confirming you can build a full multi-user app without any developer help at all [2:24] Mike's origin story: seeing Brian's build and deciding to build his own version himself [3:35] The scope of the build: sixteen planned phases, uploading a company-specific knowledge base [4:27] Realizing the concept could extend far beyond one industry, into collections, customer service, and more [4:49] The all-night build session: roughly 150 prompts in one sitting [5:07] Introducing Perplexity Comet as the AI agent handling the build almost entirely on its own [6:13] Why Brian held back on sharing this approach at first, given the $200 a month cost of the tool [6:33] The progression from prompting AI yourself to letting an AI agent handle the whole process [7:14] Mike's own track record building apps in Lovable, including sports betting projects [7:34] The bigger lesson: talk to AI like a person and keep digging past its first answer [8:24] Touring the app: the war room command center and call history tracking [8:44] The role-play arena: text-based for now, with voice role-play already tested separately [9:33] How the AI-voice role-play grades a rep's pitch and gives improvement feedback [10:17] The intelligence section: outcomes, best calling times, and conversion trends [10:55] The objection bot, covering common objections reps can practice against [11:19] The leaderboard and personal performance report for individual reps [11:43] The manager's coaching console, including trend-based coaching assignments [12:05] The training academy, built for onboarding new hires with uploaded product training [12:38] The coaching console showing rep activity and live call listen-in capability [13:01] Wrapping the tour with the reporting section [13:41] What's coming in phase 13: real-time AI listening for objection handling during live calls   5 Key Takeaways You Don't Need a Developer Until You're Scaling — For most single-build apps, you likely won't need to bring in a developer until you're serving somewhere in the range of a thousand users. Before that point, your own time is usually better spent elsewhere anyway once the app is working. Multi-User Apps Are Fully Buildable Without Code — A complete app with individual logins, private databases, and end-to-end functionality can be built without any developer involvement, using tools like Lovable. AI Agents Can Now Build Almost Autonomously — The next stage after prompting AI yourself is letting an AI agent take your idea, write its own prompts, and execute the build in another tool like Lovable with minimal hands-on involvement from you. Talk to AI Like You're Talking to a Person — The single biggest lesson from this demo is treating AI as a real back-and-forth conversation partner. Don't settle for the first answer; keep digging to surface ideas you wouldn't have found otherwise. One Internal Tool Can Apply Far Beyond Its Original Use Case — What started as a sales coaching tool for one specific industry was quickly recognized as applicable to collections, customer service, and virtually any team that handles live conversations with customers.   Links & Resources Lovable (the AI app-building platform used to build the demoed app) — https://lovable.dev Perplexity Comet (the AI browser/agent used to autonomously drive the Lovable build) — https://www.perplexity.ai/comet ChatGPT (referenced as the model powering the voice role-play feature) — https://chatgpt.com Claude (referenced as a tool Mike used elsewhere, including for a fantasy baseball draft) — https://claude.ai   Enjoyed This Episode? If this demo made you realize you could build the internal tool you've been putting off, don't wait for the "perfect" build plan, start talking to AI about the problem and keep pushing past its first answer. Share this episode with a sales leader who's still doing rep coaching manually, and if it helped, hit subscribe and pass it along to a friend or colleague.

In this live case study session from the AI for Business event, team member DeMar walks the room through a custom internal tool he built with zero coding experience: a real-time business intelligence dashboard that replaced a $200,000-plus custom-developed system the company had been paying outside developers to build over three or four years. DeMar rebuilt the same functionality himself, working with AI, in under a month. The dashboard pulls live data from ad accounts, Zoom, payment processors, and CRM systems into one place, something DeMar's team previously had to manually gather from five or six different sources for their morning meetings. He demos a live events dashboard tracking ad spend, revenue, and real-time Zoom attendee counts, a system for comparing performance across different past events, and a custom order processing tool that solved billing limitations neither Infusionsoft nor Stripe could handle. He closes with two of the build's most powerful features: a sales team activity tracker that flags duplicate bills and chargebacks automatically, and a "chat with your data" feature that lets anyone on the team ask plain-English questions and get instant answers from the numbers.   Timeline Summary [0:01] Opening framing: build the tool that solves the gap you or people close to you are struggling with [0:33] Introducing the business intelligence system and the problem of pulling numbers from five or six sources [1:21] DeMar's technical background: zero coding experience, directing developers instead [1:44] The old system cost over $200,000 and took three to four years to build [2:16] The core challenge: individually great tools that never talk to each other [2:41] Live demo of the events dashboard, showing real data flowing in [3:00] Tying the dashboard to ad accounts to show spend and net profit in real time [3:29] Solving the Zoom problem: seeing live registration and attendance instead of waiting for a report [4:07] Comparing current event performance against past events in real time [4:30] What the system would have cost to build externally versus what it actually cost [5:16] Tracking every variation of a live pitch during a single event automatically [5:51] The order processing problem: Infusionsoft's rigid billing cycle limitations [6:40] Why Stripe's custom plans still required manually chasing clients for payment [6:59] Building a custom system that bills exactly when and how they want [7:20] The real cost comparison: roughly $3,000 a month with Infusionsoft, replaced for a fraction of that [7:59] Why building for your own specific business beats forcing a generic tool to fit [8:39] The chat bubble feature: going back and forth with AI before committing to a build [9:35] Building in phases, starting with the dashboard and testing each feature before moving on [10:18] Audience question: how the system tracks the sales team's calls and messages [11:08] How the system catches human error: duplicate bills and chargebacks flagged automatically [12:00] The "chat with your data" feature: asking any question about the numbers in plain English [12:35] How the internal tool turned into client demand after sharing it at a mastermind   5 Key Takeaways Build What You Already Need — The best tool to build is usually the one solving a problem you or your team already has every day. DeMar's dashboard exists because his team was manually pulling numbers from five or six sources every morning. You Don't Need to Code to Build Real Software — DeMar rebuilt a $200,000-plus, multi-year custom system himself in under a month, with zero coding experience, simply by directing AI tools clearly and testing as he went. Use the Chat Feature Before You Build — Go back and forth with the AI to fully develop an idea before committing to building it. AI tends to agree and start building prematurely, so pushing back and refining first produces a better result. Build in Phases, One Feature at a Time — Rather than attempting the entire system at once, start with one piece, like a dashboard, get it fully working, and only then move to the next feature. Internal Tools Can Become External Products — What starts as solving your own team's problem can turn into real client demand once others see it. DeMar's team wasn't planning to sell the system until they shared it at a mastermind and clients started asking for their own version.   Links & Resources GoHighLevel (CRM referenced as part of their existing tool stack) — https://www.gohighlevel.com/9683a6 Zoom (webinar platform integrated into the dashboard) — https://www.zoom.com/ Stripe (payment processor referenced for its billing limitations) — https://stripe.com/ Infusionsoft (legacy CRM/billing platform referenced for its billing limitations) AI for Business community (referenced as the mastermind where the tool was first shared) — https://go.aiforbusiness.com/start   Enjoyed This Episode? If this case study got you thinking about the manual process your own team repeats every week, that might be your version of DeMar's dashboard. Start by naming the actual gap, not a generic idea, and build toward that one problem first. Share this episode with a business owner who's paying thousands a month for tools that still don't talk to each other, and if it helped, hit subscribe and pass it along to a friend or colleague.  

In this live workshop session from the AI for Business event, the speaker who personally built Revven walks the room through how he did it: using an AI app-building platform called Lovable to create real, working software just by describing what he wanted in plain English. He calls the concept becoming an "app-preneur," building and selling custom apps and websites as a business, without needing to code, design, or hire a developer. He makes the case that this is the same kind of shift as the SEO wave of the mid-2000s or the social media wave of the early 2010s: a new, low-barrier skill that rewards whoever moves early. His core advice is to look inward first, build something that solves a real problem inside your own business, because if you have that problem, other people in your industry almost certainly do too. From there, he breaks down the profit models available, from selling templates and building custom apps for clients to ongoing hosting and maintenance fees, before getting into his practical playbook: planning before prompting, building in phases instead of one giant request, and using a dedicated knowledge file so the AI never loses context on the project.   Timeline Summary [0:01] Introducing the topic: becoming an app-preneur and building apps and websites with AI [1:06] A show of hands: who in the room has already started building with AI [1:47] The speaker's own credentials as a top 1% builder on Lovable [2:05] The session agenda: what an app-preneur is, an intro to Lovable, and a live demo [3:29] What an app-preneur is, and how the speaker became one almost by accident [3:50] The internal company need that led to building the app that became Revven [4:41] Coining the term "minimum lovable product" instead of MVP [5:08] Selling templates for the first time, and how fast they sold out [5:49] Why looking inward at your own business's problems beats chasing something shiny and new [7:19] A real internal example: building a tool to pull scattered business numbers into one place [7:55] Comparing this moment to the SEO wave of 2005 and the social media wave of 2010 [9:22] What Lovable actually is: real, ownable code, unlike some competing platforms [10:13] How Lovable has evolved: built-in database, built-in AI, no more copying API keys [11:21] The range of things you can build: landing pages, dashboards, CRMs, chatbots, and more [12:58] Why planning takes up roughly 60% of the time on any given build [13:40] Starting with one problem, one audience, and one app to keep things simple [14:05] Building for a buyer, not just yourself, even when solving your own problem first [14:45] Agent mode versus planning mode, and why knowing the difference matters [15:23] Building in phases instead of one giant prompt, and why long prompts confuse the AI [16:16] Why your knowledge file is the secret weapon behind every consistent build [16:51] The profit models: template sales, done-for-you deployments, hosting, and maintenance fees [18:16] SaaS subscriptions and lead generation tools as additional profit angles [19:32] The playbook gift, prompt build sequences, and auditing before you sell   5 Key Takeaways Solve Your Own Problem First — The best app idea is usually already inside your own business. If something is a headache for you, there's a strong chance everyone else in your industry has the exact same headache, which means a ready market before you've sold a single copy. Plan Before You Prompt — Roughly 60% of a build's time should go into planning, not typing prompts. A weak plan costs more time and money down the line than the extra planning ever would have. Build in Phases, Not One Giant Prompt — Long, everything-at-once prompts confuse the AI and produce worse results. Breaking a build into smaller, sequential steps, sometimes dozens of them, produces a cleaner, more reliable app. A Knowledge File Is Your Secret Weapon — Keeping a dedicated file of everything the AI needs to know about a project means every single prompt pulls from consistent context, instead of the AI forgetting details between requests. There's More Than One Way to Profit — Beyond simply selling an app once, the real money is in template sales, custom done-for-you builds, and ongoing hosting and maintenance fees that turn a single project into recurring monthly revenue.   Links & Resources Lovable — https://lovable.dev ChatGPT — https://chatgpt.com Google Gemini — https://gemini.google.com Claude — https://claude.ai AI for Business Pro / Revven — https://go.aiforbusiness.com/ai4b-pro?_go=d1xyg5    Enjoyed This Episode? If this session got you thinking about a problem in your own business that a custom tool could fix, don't overthink it, just start with one problem, one audience, and one simple app. Share this episode with someone who's been putting off learning this stuff because it sounds too technical, and if it helped, hit subscribe and pass it along to a friend or colleague.