Slide 1

Slide 1 text

Prompt. Build. Repeat. The Vibe Coding Mindset Daniel Sogl @sogldaniel Software architect

Slide 2

Slide 2 text

Daniel Sogl • Software architect @ Thinktecture AG • MVP – Developer & Web Technologies • Focus: Angular and Generative AI • Socials: https://linktr.ee/daniel_sogl About me The Vibe Coding Mindset Prompt. Build. Repeat.

Slide 3

Slide 3 text

• Lovable: $0 → $100M ARR in 8 months • Cursor: $100M ARR in 12 months, $2.5B valuation • GitHub Copilot: $400M ARR, 281% growth BUT... • 95% of AI pilots fail to achieve revenue acceleration • 42% of companies abandoned AI initiatives in 2025 • 19% slower coding despite feeling 20% faster Prompt. Build. Repeat. The Vibe Coding Mindset $100M Paradox https://mlq.ai/media/quarterly_decks/v0.1_State_of_AI_in_Business_2025_Report.pdf https://beam.ai/agentic-insights/why-42-of-ai-projects-show-zero-roi-(and-how-to-be-in-the-58-) https://metr.org/blog/2025-07-10-early-2025-ai-experienced-os-dev-study/

Slide 4

Slide 4 text

Vendor Claims vs Reality The Marketing: • GitHub Copilot: 55% faster task completion • Amazon CodeWhisperer: 57% speed improvements • Cursor users report: 5-10x productivity multipliers • 96% of developers use Copilot the same day they install it Prompt. Build. Repeat. The Vibe Coding Mindset The Promise Machine https://github.blog https://aws.amazon.com/q/developer/ https://cursor.com/students

Slide 5

Slide 5 text

Controlled Study: 16 Experienced Developers, 246 Real Tasks • Actual performance: 19% SLOWER with AI tools • Developer perception: Believed they were 20% faster • Perception gap: 40 percentage points difference • Tool used: Cursor with Claude Sonnet 3.5 Prompt. Build. Repeat. The Vibe Coding Mindset Reality Check - The METR Study https://metr.org/blog/2025-07-10-early-2025-ai-experienced-os-dev-study/

Slide 6

Slide 6 text

GitClear Analysis: 153-211 Million Lines of Code • Code churn: Projected to double in 2025 • Copy-pasted code: 8.3% → 12.3% (+48%) • Code refactoring: 25% → <10% (-60%) • Delivery stability: 7.2% decrease (Google DORA Report) Prompt. Build. Repeat. The Vibe Coding Mindset Code Quality Catastrophe https://www.gitclear.com/ai_assistant_code_quality_2025_research

Slide 7

Slide 7 text

Veracode 2025 Study: AI Code Security Failures • 45% of AI-generated code fails security tests • Java security failure rate: 72% • Secret leakage: 40% higher in Copilot repos Prompt. Build. Repeat. The Vibe Coding Mindset Security Nightmare https://www.veracode.com/blog/genai-code-security-report/ https://blog.gitguardian.com/yes-github-copilot-can-leak-secrets/ https://snyk.io/reports/ai-code-security/

Slide 8

Slide 8 text

From Andrej Karpathy Tweet to Cultural Phenomenon • February 2nd, 2025: Karpathy coins the term • Now in Webster's Dictionary • Meme status: "Vibe coding is easy. Vibe debugging is the hard part" Prompt. Build. Repeat. The Vibe Coding Mindset Enter "Vibe Coding"

Slide 9

Slide 9 text

Prompt. Build. Repeat. The Vibe Coding Mindset

Slide 10

Slide 10 text

Not All AI Coding Is Vibe Coding • AI Typing Assistant: Code completion, suggestions • AI Pair Programming: Collaborative problem- solving • True Vibe Coding: "Forget the code exists" Prompt. Build. Repeat. The Vibe Coding Mindset The Vibe Spectrum

Slide 11

Slide 11 text

The Stakes Are Higher Than You Think • 50,000+ organizations using GitHub Copilot • 41% of all code is now AI-generated • Path to a billion programmers (GitHub CEO) • $326.2B market by 2035 (low-code platforms) The Critical Question: Are we democratizing development or industrializing technical debt? Prompt. Build. Repeat. The Vibe Coding Mindset Why This Matters https://www.elitebrains.com/blog/aI-generated-code-statistics-2025 https://www.netcorpsoftwaredevelopment.com/blog/ai-generated-code-statistics https://blog.github.com

Slide 12

Slide 12 text

Why coding tools fail to support you • LLMs were trained on older data • LLMs don’t understand your architecture without help • LLMs don’t know your company domains • LLMs don’t know your coding standards • Developers don’t write prompts describing every edge case or needed context to solve tasks • Different tasks require different context Prompt. Build. Repeat. The Vibe Coding Mindset Limitations of LLMs

Slide 13

Slide 13 text

Simplify your prompts • Project-specific coding standards • Architectural patterns and constraints • Domain knowledge embedding • Step-by-step reasoning requirements How to generate?: - Ask the AI to analyze your codebase - Use predefined instructions – Itterateive update your instructions Prompt. Build. Repeat. The Vibe Coding Mindset Fighting Back - Custom Instructions

Slide 14

Slide 14 text

AGENTS.md • The problem: each tool uses different file names for custom instructions • AGENTS.md aims for becoming supported by all AI tools Prompt. Build. Repeat. The Vibe Coding Mindset Standardization of Custom Instructions

Slide 15

Slide 15 text

The key for ”intelligent” workflows • Open-source protocol developed by Anthropic • Provides a consistent way for LLMs to interact with external resources • Client-Server architecture: AI applications (clients) request context from external services (servers) • Official servers are available for GitHub, Atlassian, Playwright, Stripe, Databases and more • It’s the key to useful AI-coding setups in complex environments Prompt. Build. Repeat. The Vibe Coding Mindset Model Context Protocol (MCP)

Slide 16

Slide 16 text

Prompt. Build. Repeat. The Vibe Coding Mindset MCP workflows Developer asks: “Explain failing tests in PR #42.” Copilot calls GitHub MCP → fetches PR diff + CI log LLM reviews context → returns root-cause & fix steps Dev clicks “Apply fix” → Copilot edits code & opens new PR

Slide 17

Slide 17 text

• Not all LLMs are equal: Performance varies widely • Understand reasoning vs. non-reasoning models • Context size matters greatly in coding scenarios • Benchmarks help guide practical model choice • Cost per 1 million input/output tokens Prompt. Build. Repeat. The Vibe Coding Mindset Choosing the right LLM for your tasks

Slide 18

Slide 18 text

Prompt. Build. Repeat. The Vibe Coding Mindset Popular LLMs for software development Model Provider Reasoning Context Window SWE-bench $ / 1M tokens Claude 4 Opus Anthropic 200k tokens 72.5 % $15 / $75 Claude 4 Sonnet Anthropic 200k tokens 72.7 % $3 / $15 GPT-5 (high) OpenAI 400k tokens 74.9 % $1.25 / $10 GPT-o3-mini (high) OpenAI 200k tokens 49.3 % $1.10 / $4.40 Gemini 2.5 Pro Google 1M tokens 63 % $1.25 / $10 DeepSeek V3 DeepSeek 163k tokens 38.3 % $0.25 / $0.85 Grok 4 xAI 256k tokens 72 % $3 / $15 Kimi K2 Moonshot 131k tokens 65.8 % $0.13 / $0.13

Slide 19

Slide 19 text

CO-STAR Framework for Coding • Context: Project background, constraints • Objective: Specific goals, success criteria • Style: Coding patterns, conventions • Tone: Collaborative, step-by-step • Audience: Experience level, domain • Response: Format, structure requirements Prompt. Build. Repeat. The Vibe Coding Mindset Prompt Engineering That Works

Slide 20

Slide 20 text

AI-Powered Code Review Pipeline Tools & Impact: • CodeRabbit, GitHub Copilot, Google Gemini • Automated test generation: 80%+ coverage • Snyk DeepCode AI: Pre-production security scanning • Human focus: Business logic, architecture New Workflow: Code → AI Review → AI Tests → Human Review → Deploy Prompt. Build. Repeat. The Vibe Coding Mindset Quality Assurance Revolution

Slide 21

Slide 21 text

How to Do AI Coding Right Setup: • Define custom instructions/rules files • Configure MCP servers for your stack • Choose task-appropriate LLMs Process: • Use CO-STAR prompt framework • Require AI to explain before coding • Implement automated testing generation • Maintain human review of critical paths Quality: • Run security scans on all AI code • Measure actual vs perceived productivity • Track technical debt metrics Prompt. Build. Repeat. The Vibe Coding Mindset Best Practices Checklist

Slide 22

Slide 22 text

Prediction vs Preparation Inevitable Trends: • More autonomous coding agents • Natural language becomes primary interface • AI handles increasingly complex tasks Critical Decisions Today: • How do we maintain code quality? • What skills should humans develop? • How do we ensure security and privacy? Prompt. Build. Repeat. The Vibe Coding Mindset The Future We're Building

Slide 23

Slide 23 text

Your Next Steps 1. Experiment Responsibly • Start with low-risk projects • Implement quality safeguards first • Measure Everything Track actual productivity (not perception) • Monitor code quality metrics • Assess security vulnerabilities 2. Invest in Skills • Prompt engineering techniques • AI tool orchestration • Quality assurance processes Prompt. Build. Repeat. The Vibe Coding Mindset Call to Action

Slide 24

Slide 24 text

Prompt. Build. Repeat. The Vibe Coding Mindset The best developers won’t be replaced by AI, they’ll be the ones who learn to wield it

Slide 25

Slide 25 text

Thanks for your attention Daniel Sogl @sogldaniel [email protected]