Successfully coding with AI in large enterprises: Centralized rules, workflows for tech debt, and training your team | Zach Davis (Director of Engineering at LaunchDarkly)

Zach Davis is a product-minded engineering leader and builder at heart, with over 12 years of experience building high‑performing teams and crafting developer tools at companies like Atlassian and LaunchDarkly. In this episode, he shares how he’s helping his 100-plus-person engineering team successfully adopt AI tools by creating centralized documentation, using agents to tackle technical debt, and improving hiring processes—all while maintaining high quality standards in a mature codebase. What you’ll learn: 1. How to create a centralized rules system that works across multiple AI tools instead of duplicating documentation 2. A systematic approach to using AI agents like Devin and Cursor to analyze and reduce test noise in large codebases 3. How to leverage AI tools to document your codebase more effectively by extracting knowledge from existing sources 4. Why “what’s good for humans is also good for LLMs” should guide your documentation strategy 5. A custom GPT workflow for improving interview feedback quality and coaching interviewers 6. How to approach tech debt reduction with AI by creating prioritized task lists that both humans and AI agents can work from — Brought to you by: WorkOS—Make your app enterprise-ready today Lenny’s List on Maven—Hands-on AI education curated by Lenny and Claire — Where to find Zach Davis: LaunchDarkly: https://www.launchdarkly.com LinkedIn: https://www.linkedin.com/in/zach-davis-28207195/ — Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo — In this episode, we cover: (00:00) Introduction to Zach Davis (02:44) Overview of AI tools used at LaunchDarkly (04:00) The importance of having someone responsible for driving AI adoption (05:44) Why vibe coding isn’t acceptable for enterprise development (06:42) Making engineers successful with AI on their first attempt (07:55) Creating centralized documentation for both humans and AI agents (10:19) Using feature flagging rules to improve AI outputs (12:33) Advice for getting started with rules (14:28) Demo: Setting up Devin’s environment in a large codebase (24:33) Devin’s plan overview (27:55) Demo: Creating a prioritized tech debt reduction plan (36:40) Demo: Using AI to improve hiring processes and interview feedback (40:34) Summary of key approaches for integrating AI into engineering workflows (42:08) Lightning round and final thoughts — Tools referenced: • Cursor: https://www.cursor.com/ • Devin: https://devin.ai/ • ChatGPT: https://chat.openai.com/ • Claude: https://claude.ai/ • Windsurf: https://windsurf.com/ • Lovable: https://lovable.dev/ • v0: https://v0.dev/ • ChatPRD: https://www.chatprd.ai/ • Figma: https://www.figma.com/ • GitHub Copilot: https://github.com/features/copilot — Other references: • Jest: https://jestjs.io/ • Vitest: https://vitest.dev/ • MCP: https://www.anthropic.com/news/model-context-protocol • Confluence: https://www.atlassian.com/software/confluence — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [redacted email].