Send us a text

We 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 forgot

For 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: $0

Here'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 text

Watch the full episode on youtube (or Spotify): https://www.youtube.com/watch?v=ttf2tQy0x_U

We 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 lives

Saves 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 adder

They 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 #appdevelopment

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 text

I 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 charts
• 8-question assessment tool with scoring
• SWOT analysis generator
• Personalized recommendations engine

All released for FREE at bonanza-studios.com

The Secret: PRD-First Vibe Coding

Most 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 wanted
• Iterated on wireframes Claude generated for me
• Got the file structure, database schema, and tech stack right
• Clarified every detail until the PRD was bulletproof

Then 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 project
• With vibe coding: 3 weeks from concept to production

The 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.com

If it's possible for me, it's possible for you. Welcome to the vibe coding era.

#ClaudeCode
#VibeCoding
#AIDevelopment
#PRDFirst
#VoiceToCode
#AIProductDevelopment
#DigitalTransformation
#RapidPrototyping

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/