Developer Productivity – DIY (with LLM) or How I Learned to Stop Worrying and Love the AI
summary
Live demo shows concrete wins: enabling Gradle build scan and remote caching avoids 11 tasks and saves ~56 seconds, and setting MaxParallelForks to runtime.getRuntime().availableProcessors() cuts a test run from ~60s to ~6s (6x). The talk explains building a ChatGPT embedding plugin using a vector DB, notes the plugins API is closed beta, and recommends services like Mantium as a plugin-as-a-service. Predictive test selection trains on historic changes and reaches ~97–99% accuracy, letting teams skip ~30% of local tests safely.
AI-written summary · about
chapters (17)
- 0:00Introduction
- 1:15Speaker background
- 2:43Developer productivity overview
- 5:56Key principles
- 9:49Improving build strategies
- 10:33Live demo: Java builds
- 13:21Gradle Build Scan insights
- 17:40Gradle Enterprise to Velocity
- 19:27Challenges with ChatGPT for recent tech
- 21:44Custom ChatGPT plugins
- 24:41Mantium plugin service
- 26:39Build performance with Velocity
- 27:23Parallelizing tests
- 30:32AI test selection
- 33:21Predictive test selection deep dive
- 39:42Summary
- 40:03Q&A
related talks
33mDeveloper Productivity – How I Learned to Stop Worrying and Love the AI
32mDeveloper Productivity – DIY (with ChatGPT).
54mDeveloper Productivity Engineering Deep Dive
36mDeveloper Productivity Engineering: What's in it for me?
01h 02mPANEL - Unleashing the Future: The Impact of Gen AI on Development Productivity
36mUnleashing Generative AI: Improving Developer Productivity in SRE
48mMastering the AI Shift: Adaptive Strategies for Software Evolution
29mGenAI in Backstage - Turbocharge Your Developer Productivity!