UX for AI

Send us a textWe were wasting several hours a month on time-off requests. So we built an app for it.Every time someone needed a day off, it was the same dance:+ Send a message to the team+ Create a calendar invite+ Update the project manager+ Hope nobody forgotFor a small team where every hour counts, this was ridiculous.So my colleague Jarek built us a custom time-off management system using Figma Make and Supabase.The result?✓ Completely automated approval workflow ✓ Auto-syncs with Google Calendar ✓ Posts directly to our ClickUp channels ✓ Cost: $0Here's what really hit me though...We were ready to upgrade our project management tool, add $10-20/user/month, just to get this ONE feature.Instead, we spent a week building exactly what we needed.The bigger lesson:Once you build your first internal tool, you start seeing opportunities everywhere. "Should we upgrade for that feature?" becomes "Could we build that ourselves?"This isn't just about saving money on subscriptions. It's about:👉 Moving faster (no vendor research, no procurement)👉 Staying flexible (switch tools anytime without losing functionality)👉 Keeping control (your data, your rules, your customization)This mindset shift is massive.What's one subscription you're paying for that you could probably build yourself?Interested in joining the podcast? DM Behrad on LinkedIn:https://www.linkedin.com/in/behradmirafshar/This podcast is made by Bonanza Studios, Germany’s Premier Digital Design Studio:https://www.bonanza-studios.com/

Send us a textWatch the full episode on youtube (or Spotify): https://www.youtube.com/watch?v=ttf2tQy0x_UWe build MVPs in 2-week sprints. This sprint is an internal “Blog Maker” app. I’m wrestling the last mile, always the hardest part of any launch.👉 What the app does + Pull YouTube videos from our channel+ Analyze transcript + do SERP/competitor checks+ Use two AI agents — researcher → writer — to draft+ Push the draft straight to Webflow for editing where it livesSaves hours per post. The writer agent repurposes for our ICP and SEO rules.👉 Why we built an app, not an automation+ Complex automations turn into field soup and never-ending maintenance. + I find it easier to change and maintain codebase. The AI agent can do most of heavy lifting rather than me clicking myself to suffocation on n8n.👉 The two-agent CTO approach + Agent 1: “CTO” — ruthless reducer+ Agent 2: “Visionary” — blue-sky adderThey argue over the same prompt. I cherry-pick, then iterate the prompts every run. I find giving long prompts to one agent is a bad practice. just produces garbage.👉 Lesson learned: I burned ~$150–200 on API calls testing YouTube transcript paths so far in less than a week. Should’ve used a reliable paid API for transcripts and moved on. 👉 Status right now:Content quality is there (2,500–3,000 words), SEO linter checks are running, but markdown + external linking still need love before I auto-publish.👉 Tool stack:Stack (today): cloud code (plan-mode), ChatGPT-Codex (debug mode), a lot of terminal, Git. I let cloud code run with full permission (YOLO), then review.Part 2 next week: either “celebration mode” or “here’s the fix I shipped.” If you want me to share the two-agent prompt skeleton or file structure, comment “AGENTS”.P.S. At Bonanza Studios | Digital Transformation, we run bi-weekly sprints building MVPs like this for mid-market digital teams. Your idea that's been stuck in meetings for months? We develop it in 2 weeks. DM if you're interested.#MVP #AIPROTOTYPING #claude #MVP #appdevelopmentInterested in joining the podcast? DM Behrad on LinkedIn:https://www.linkedin.com/in/behradmirafshar/This podcast is made by Bonanza Studios, Germany’s Premier Digital Design Studio:https://www.bonanza-studios.com/

Send us a textI just shipped a 25-page interactive handbook with calculators, charts, and a full assessment tool in 3 weeks. Total time that would've taken traditionally? An entire quarter.What I Built:9-chapter Digital Readiness Handbook (25 pages)Interactive elements, calculators, live charts8-question assessment tool with scoringSWOT analysis generatorPersonalized recommendations engineAll released for FREE at bonanza-studios.comThe Secret: PRD-First Vibe CodingMost people jump straight into building. I spent 3 DAYS on the PRD (Product Requirements Document) talking to Claude—literally talking, not typing.Using Mac Whisper, I:Described every screen I wantedIterated on wireframes Claude generated for meGot the file structure, database schema, and tech stack rightClarified every detail until the PRD was bulletproofThen I handed it to Claude Code. The build phase? Few hours here, few hours there. Not full-time grinding. The tool built while I worked on other things.Why This Matters for You:If you're a digital leader at a mid-market company or SMB, this changes your timeline calculations:Traditional: 1 quarter for a complex digital projectWith vibe coding: 3 weeks from concept to productionThe key? Invest heavily in your PRD. Talk through it. Make Claude wireframe for you. Get every detail right BEFORE you build.Tools I Used:Claude Sonnet 4.5 (for PRD creation)Claude Code (for development)Mac Whisper (for voice-to-text)This is the most seamless vibe coding project I've executed. Zero major bottlenecks. Why? The PRD was airtight.Stop rushing into builds. Start with conversations. Let AI help you think, then let it help you build.Check out the Readiness Handbook yourself: bonanza-studios.comIf it's possible for me, it's possible for you. Welcome to the vibe coding era.#ClaudeCode#VibeCoding#AIDevelopment#PRDFirst#VoiceToCode#AIProductDevelopment#DigitalTransformation#RapidPrototypingInterested in joining the podcast? DM Behrad on LinkedIn:https://www.linkedin.com/in/behradmirafshar/This podcast is made by Bonanza Studios, Germany’s Premier Digital Design Studio:https://www.bonanza-studios.com/

Send us a textYou’re probably burning tokens on an AI feature your users don’t want.You’re not alone. Lots of teams are forcing “AI-native” into products.Here’s the good news: Lean Startup still applies to AI. You can validate the experience without writing a single line of app code.👉  The No-Code AI MVP (my playbook)Goal: simulate your production AI service in a controlled “cloud project” so you can iterate.1. Define outcomes, not features. What must the AI accomplish that a user would pay for?2. Write the system brief. Tone, boundaries, escalation rules, guardrails.3. Seed context (“memory”). Drop your internal docs. 4. Mimic RAG. Keep a simple database (call it Memory) and paste each full conversation into it. Force the agent to read Memory first on the next turn.5. Design success criteria you can score.6. Operate it yourself. Founder + team use it daily. Track token spend, failure reasons, retrieval misses.7. Tight feedback loop. Adjust instructions and Memory structure. Re-run the same tasks. (don't forget: create a log of all the changes so you can retrace your steps)8. Decide. When quality and cost are predictable, then (and only then) think UI, auth, billing.Cost is a product decision! Your token diet can make or break the business. Bottom line: Build the AI service right before you build around it. P.S. If you’re building an AI-led product, DM me “PROTOTYPE.” I’ll walk you through the exact worksheet and Memory schema we used in this video.#Prototyping #AI #AInative #RAG #MVP #uxInterested in joining the podcast? DM Behrad on LinkedIn:https://www.linkedin.com/in/behradmirafshar/This podcast is made by Bonanza Studios, Germany’s Premier Digital Design Studio:https://www.bonanza-studios.com/

Send us a textPlease check our podcast on Spotify for the video.For MVP projects, we don't create high-fidelity designs for every single screen anymore. Our designer creates key screens in high-fidelity, then AI generates the entire design system and front-end ready UI components.To prove this workflow works with even less, I took it further. Started with a single screenshot from Dribbble i.e. NO Figma file!The results? See the video.Our workflow these days+ Design Sprint workshop (2 weeks) to align on the scope, concept and develop key wireframes+ Designer creates core screens (high-fidelity) (<3 days)+ AI generates complete component library (1-2 days)+ Developers receive production-ready front-end (same day)Claude + ChatGPT Codex working together is more powerful than most digital leaders realize.What this means for you:Traditional timeline: 3-4 weeks for design → 2-3 weeks for front-end development = 5-7 weeks before backend work starts.👉 New timeline: 1 week for complete front-end = Backend integration begins Week 1.Your developers aren't waiting anymore. Your stakeholders can view the full front-end ready app and interact with it within a week. Your credibility as a digital leader compounds with each early win.The companies moving fastest in 2025 aren't the ones with the biggest development teams. They're the ones who tap into the right tools, processes, and team.P.S. Bonanza helps digital leaders ship MVPs way faster within weeks. Our AI-accelerated workflow delivers production-ready front-ends in days, not weeks, giving you the speed to prove value in your first 90 days. Whether you need rapid prototyping, full product development, or a strategic partner who understands the pressure you're under, we deliver results that build your credibility with the board. Interested in joining the podcast? DM Behrad on LinkedIn:https://www.linkedin.com/in/behradmirafshar/This podcast is made by Bonanza Studios, Germany’s Premier Digital Design Studio:https://www.bonanza-studios.com/

Send us a textVideo is uploaded on Spotify.JUST WOW!! Claude Imagine is hands down the most exciting build platform I've tested.I just prototyped two complex applications in 10 minutes. A real-time sales assistant and a trading app with live data. Watch the demo - the Cloud imagine interface alone is super cool:+ A meditative desktop environment that feels like creative flow+ A simple prompt widget where you just describe what you want and also talk to you in a way+ Build speed genuinely shocking (I mean REALLY fast)I can see myself living in this environment day in and day out. And when they connect it to Figma so I can tweak designs and bring them back? 😍.I've tried everything:+ Bolt + Lovable + Replit + ChatGPT Nothing matches Claude Imagine's speed from imagination to execution. As someone dealing with constant prototyping, client demos, or product validation - I need this badly.Make no mistake - this is a race!Claude Code & Imagine, ChatGPT Codex, Figma Make, Bolt, Lovable - whoever helps you build fastest wins.P.S. Want to learn how to leverage Claude Code & Imagine for your innovation pipeline? Bonanza Studios helps mid-market teams implement AI-powered prototyping that ships in days.Interested in joining the podcast? DM Behrad on LinkedIn:https://www.linkedin.com/in/behradmirafshar/This podcast is made by Bonanza Studios, Germany’s Premier Digital Design Studio:https://www.bonanza-studios.com/

Send us a textFame Razak shares his approach to building MVPs in just ten days, blending UX design, AI tools, and dev workflows. He talks through past projects with brands like HSBC and Nike and his process for product ideation and scoping. A must-listen for anyone shipping fast and thinking deeply.Interested in joining the podcast? DM Behrad on LinkedIn:https://www.linkedin.com/in/behradmirafshar/This podcast is made by Bonanza Studios, Germany’s Premier Digital Design Studio:https://www.bonanza-studios.com/

Scott Jones, an AI product management expert at Realize, shares his unique journey from improv to the forefront of responsible AI. He discusses how neurodivergent perspectives can innovate tech for societal good. The conversation delves into the intersection of art and intuition in the AI landscape, emphasizing the value of taste in technology. Jones also reflects on AI's disruption of traditional roles and the ethical imperative for privacy and fairness in AI applications, spotlighting innovative identity verification methods in digital transactions.

Explore the frustrations of using AI platforms for building landing pages. The host reveals the limitations of template-based tools like Lovable, stressing their uniformity. Find out how Cursor became a game-changer, allowing for greater customization. The discussion emphasizes the value of coding skills in unleashing creativity and control in web design. Dive into the reality of no-code platforms and discover why uniqueness still matters in a sea of sameness.

Send us a text Tomi shares how his obsession with sound led him from building cars to composing award-worthy symphonies—and developing ZenyAI, an AI platform that turns game scenes into dynamic soundscapes. Listen to Tomi's work: https://www.youtube.com/watch?v=aIhcUYPSTfcYou can find Tomi here: https://www.linkedin.com/in/tomi-oladunjoye-703a69204/Interested in joining the podcast? DM Behrad on LinkedIn:https://www.linkedin.com/in/behradmirafshar/This podcast is made by Bonanza Studios, Germany’s Premier Digital Design Studio:https://www.bonanza-studios.com/