From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud
Thundra built a runtime intelligence layer enabling coding agents to continuously fix production performance issues.
“Google just published their Dora metrics for 2026 and we can see that the biggest impact of AI adoption on engineering is individual effectiveness... But the second one is software delivery instability.”
Thundra's CTO describes an agentic workflow that continuously monitors and optimizes production application performance by capturing functional-level runtime context for coding agents. The talk surfaces a notable finding from Google's 2026 DORA report: AI adoption is boosting individual developer effectiveness but simultaneously increasing software delivery instability. This tension between perceived speed and system-level reliability is the core engineering challenge the product aims to address.