Code:
https://github.com/ai-that-works/ai-t...
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
00:00 Introduction to Live Coding and BAML
05:41 Specifying the Solution: Documentation and Syntax
11:14 Live Coding: Implementing Timeouts
16:34 Researching the Codebase for Timeouts
21:29 Finalizing the Implementation Plan
32:27 Inline Code Examples and Client SDK Generation
37:54 Understanding Timeout Mechanisms
48:51 Leveraging AI for Code Implementation
53:41 Reading and Reviewing Implementation Plans
59:01 Phase One: Parsing and Validation
01:05:06 Refining the Development Process
01:11:25 Testing and Implementation Strategies
01:17:23 AI Model Utilization in Development
01:23:25 Error Detection and Client Handling
01:28:08 Understanding Typographical Errors
01:32:26 Timeouts and Error Management
01:35:59 Compilation and Verification Processes
01:44:45 Integrating Testing with PyTest
01:48:19 Implementing Timeout Functionality
01:54:44 Refactoring and Error Handling
02:03:37 Finalizing Python Tests and Commit