How to start building your custom tool

There’s a whole narrative right now that “vibe coding is a bubble” and all the MRR from AI-built apps isn’t real.

In this episode, we chat with Jacob Klug, founder of the agency Creme, which specializes in building lovable MVPs on top of tools like Lovable and AI coding assistants. Jacob makes the case that most of the “AI apps are trash” discourse is really a skill issue, not a tool issue—and he breaks down the exact process his team uses to ship full platform-level apps in two-week sprints.

We dig into how to scope and design software that doesn’t look AI-generated, how to think about personal operating systems vs. SaaS, why ideas are getting worse even as tools get better, and how creators and agencies can turn niche domain expertise into real products.

If you’re an operator, marketer, or founder trying to figure out how to actually use AI coding tools (instead of just tweeting about them), this one’s for you.

Guest

Jacob Klug — founder of Creme, an agency building “lovable MVPs” and full-stack products with Lovable + AI tools; helps founders, startups & enterprises ship production apps in weeks without sacrificing UX.

Guest Links

Website: https://www.creme.digital/
LinkedIn: https://www.linkedin.com/in/jacob-klug-37b254156/
X (Twitter): https://x.com/Jacobsklug

What You’ll Learn

• Why the “vibe coding is a bubble” take is mostly a skill and discipline problem
• How Jacob’s agency ships full startup-grade products using Lovable and AI
• The PRD-first formula they use before ever opening a builder
• How to decide when to build vs. when to buy software in 2025
• Why we’re entering a wave of personal OSes and custom internal tools
• How to avoid shipping janky AI UI and make your app look intentionally designed
• The mindset shift from “I could build anything” → “I will build this one specific thing”
• Why specializing in one AI tool (Lovable, Cursor, n8n, etc.) beats being “the AI guy”
• Tactical content and lead-gen plays for agencies on LinkedIn and YouTube
• How to learn AI tooling without getting paralyzed by the infinite possibilities

Timestamps

• 00:00 — Vibe coding: bubble or breakthrough?
• 02:23 — Effective use of no-code tools
• 05:23 — Stack and scoping for MVP development
• 07:08 — Trends in personal software development
• 10:33 — Personal projects: blood work analysis tool
• 13:00 — Steps to start building custom software
• 17:49 — Successful and unsuccessful product categories
• 21:01 — Learning and adopting AI tools
• 27:45 — Creator collaboration in software development
• 32:14 — Lead generation strategies for AI-powered agencies

Key Topics & Ideas

1. Bubble or Skill Issue?

• Why early no-code/AI apps looked janky
• How tools like Lovable increased automation from ~50% → ~85%
• The remaining 10–15% where real engineering still matters
• Many failures come from non-devs skipping fundamentals

2. How Creme Builds Lovable MVPs

• Every project starts with a clear PRD (often drafted with ChatGPT)
• AI is used to tighten scope before building
• When Creme stays fully in Lovable vs. moving code to Cursor
• Using Lovable Cloud for hosting, database, and analytics

3. Personal Operating Systems & Internal Tools

• People replacing SaaS subscriptions with their own custom tools
• In a 20-person cohort, nearly everyone built workflow apps
• Rise of the Personal OS: one system for life + work
• Example builds:
  • Bloodwork tracker from PDF uploads
  • Unified messaging CRM (WhatsApp, Telegram, SMS, email)
  • Automated 30-second sales briefings

4. How to Learn AI Coding Tools

• Half the cohort hadn’t built anything before starting
• Main blocker: overwhelm, not skill
• Learn core concepts: frontend vs. backend, auth, roles, security
• Build daily reps, focus on the next thing you need—not “all of AI”

5. Designing Apps That Don’t Look AI-Generated

• Good design is still the hardest and biggest edge
• Creme process: build a /components library, define buttons/cards/inputs, assign stable IDs
• Tools: Mobbin, Figma Community kits, 21st.dev
• Best prompt: “Here’s a screenshot → copy this.”

6. What Works in Product Ideas

• Most of Creme’s builds are full startup platforms, not micro-tools
• AI makes shipping easier, but ideas are getting worse without depth
• Real advantage = domain expertise + niche problem + AI speed

7. Creators x Software

• Creators can now ship products without capital
• Jacob prefers retainers over equity
• Analogy: Like creator brands—most fail, a few go huge

8. Career Strategy: Specialize

• Future = verticalized expertise, not “AI generalists”
• Specialist lanes: Lovable, Cursor, n8n, automation
• Be the person for one tool + one market

9. Content & Lead Gen

• Jacob's two rules for content: people are selfish and people are bored
• Build content that teaches, sparks emotion, and creates curiosity
• Post ~5x/week, prioritize visual posts
• Long-term: YouTube deep dives for high-intent inbound

Sponsor
Today’s episode is brought to you by Graphed – an AI data analyst & BI platform.

With Graphed you can:
Connect data like GA4, Facebook Ads, HubSpot, Google Ads, Search Console, Amplitude
Build interactive dashboards just by chatting (no Looker Studio/Tableau learning curve)
Use it as your ETL + data warehouse + BI layer in one place

Ask:
“Build me a stacked bar chart of new users vs. all users over time from GA4”
…and Graphed just builds it for you.

👉 Get a 14-day free trial with 10 seats for your team: https://graphed.com/