Code:
https://github.com/ai-that-works/ai-that-works/tree/main/2025-10-14-no-vibes-allowed
Vaibhav Gupta and Dex demonstrate the power of AI-assisted coding by implementing a complex timeout feature for BAML (a programming language for AI applications) in a live coding session. Starting from a GitHub issue that had been open since March, they showcase a systematic workflow: specification refinement, codebase research, implementation planning, and phased execution. Using Claude and specialized coding agents, they navigate a 400,000+ line codebase, implementing timeout configurations for HTTP clients including connection timeouts, request timeouts, idle timeouts, and time-to-first-token for streaming responses. The session highlights key practices like context engineering, frequent plan validation, breaking complex features into testable phases, and the importance of reading AI-generated code. In under 3 hours of live coding, they achieve what would typically take 1-2 days of engineering time, successfully implementing parsing, validation, error handling, and Python integration tests.
Chapters
Introduction to Live Coding and BAML
Specifying the Solution: Documentation and Syntax
Live Coding: Implementing Timeouts
Researching the Codebase for Timeouts
Finalizing the Implementation Plan
Inline Code Examples and Client SDK Generation
Understanding Timeout Mechanisms
Leveraging AI for Code Implementation
Reading and Reviewing Implementation Plans
Phase One: Parsing and Validation
Refining the Development Process
Testing and Implementation Strategies
AI Model Utilization in Development
Error Detection and Client Handling
Understanding Typographical Errors
Timeouts and Error Management
Compilation and Verification Processes
Integrating Testing with PyTest
Implementing Timeout Functionality
Refactoring and Error Handling
Finalizing Python Tests and Commit
Transcript
I've watched this one closely. Ask me anything about it and I'll point you to the exact moment.