395: From Code Writer to Code Editor: My AI-Assisted Development Workflow

What It Covers

Arvid Kahl explains his AI-assisted development workflow, breaking down how he uses voice-to-text prompting, agentic coding tools like Gini, and Claude for building features in PodScan with a 40-20-40 time allocation method.

Key Questions Answered

• •Voice-to-Code Workflow: Use Whisper Flow to dictate detailed specifications instead of typing, speaking through current code state, desired outcomes, implementation steps, and business logic context before pasting transcripts into AI coding assistants for faster, more accurate results.
• •40-20-40 Time Distribution: Allocate 40% of development time crafting detailed prompts with repetition for critical logic, 20% waiting for AI code generation, and 40% reviewing every line to understand implementation—verbose upfront context reduces errors and iteration cycles significantly.
• •Documentation Prototyping Method: Export real production data as CSV, use Claude to condense large JSON objects with bash scripts, then feed actual data examples alongside existing documentation to generate comprehensive technical docs that are 95% accurate in minutes instead of hours.
• •Code Editor Role Shift: Developers transition from writing code to editing and approving AI-generated code, where discriminating good code from bad code becomes more valuable than typing ability—understanding algorithmic complexity and data structures remains essential for effective prompting and verification.