Salesforce research engineer reviews a year of AI use and the human-machine split
What happened
On November 4, 2026, Hacker News featured a review by a current Salesforce AI Research engineer of his AI use over the past 12 months. He says machines now write more than 90% of his code and he manages about 5–6 coding agents such as Claude Code day to day, but architecture review and manual testing stay with him, and running them in parallel leaves him tired. Outside coding, AI is his first stop for search and literature lookup, though complex research still needs judgment from human colleagues, and he keeps avoiding AI for writing his own personal expression.
Written by AI from the coverage · updated 56 minutes ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pagePickResearch engineer says AI agents now write over 90% of his code
A current research engineer at Salesforce AI Research reviewed his last 12 months of AI use and says machines now write more than 90% of his code. He runs about 5–6 coding agents such as Claude Code day to day, still reviews architecture himself and tests manually, and feels the fatigue of managing them in parallel. AI is his first stop for search and literature lookup, but complex research still needs judgment from human colleagues, and he keeps avoiding AI for writing his own personal expression.
Heat over time
Not enough continuous observations to draw a trend yet.