Dev Reports 33% Productivity Gain From Agentic Tools, Says Automation Must Come Last
yunta_tsai · x · 2026-10-07
A developer reports his productivity is roughly 33% higher than last year using agentic tools, measured by models, features and milestones delivered, with concept-to-deliverable about 3x faster and higher quality—not just coding but decision-making too.
The key, he argues, isn't whether tools are agentic but rigorously following an "algorithm":
- Make requirements less dumb
- Delete the part or process step
- Optimize
- Accelerate
- Automate
Agentic is the last step; deploying it early only accelerates slop. Routine housecleaning keeps agentic tools effective. Given the pace of model improvements, he can't imagine what work will look like soon.
More from AGI Musings
- After 12+ hours a day with AI, she writes again: it's not just attention loss, it's memory — LadyAshBorg · 2026-10-07
- AI usage inflects exponentially past capability thresholds — is research next? — menhguin · 2026-10-07
- A Decade-by-Decade Tech Recap: 2010s Delivered Nothing, 2020s Bring AGI — Darpinian · 2026-10-07
- Katja Grace: Being 'in the room' at AI labs may no longer be a high-impact path — michael_nielsen · 2026-10-07
- Bessemer's Dholakia: AI's most important uses aren't invented yet, like oil in 1870 — rohanpaul_ai · 2026-10-07
- He spent 24 years on Barnette's Conjecture — then AI solved it as problem 180 — Simon Willison · 2026-10-07