Agents, codebases, and teams — Aditya Khandelwal, Amazon AGI Lab
Aditya Khandelwal from Amazon AGI Lab shares insights on introducing AI agents into an engineering team.
The core issue isn't agent technology but adoption strategy: when only some engineers use agents while others don't, chaos ensues—those without agents fall behind, and people blame the agents for problems. Khandelwal's solution was to restructure the entire codebase workflow around a special function called "ship it" that automates everything from finished code to PR-ready status. Around this framework, the team integrated agents for code review and other tasks. It wasn't perfect—agents created thousands of open issues—but it helped engineers develop actual trust in the tools.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago