Six months after the agent keynotes, an accounting
re:Invent promised agentic development at scale. Half a year on, what shipped, what stalled, and the safeguard that tells you where this settles.
Last December's re:Invent was wall-to-wall agents: Nova 2 models, the Kiro development environment, orchestration everywhere, per Caylent's comprehensive roundup. Six months is enough distance for an accounting of the category, and the ledger is instructively split.
What visibly shipped: coding assistance as a default. The tools write scaffolding, tests and migrations across most serious engineering organizations now, and the arguments have moved from "whether" to configuration details. What visibly stalled: autonomy in production. The agent that operates infrastructure unsupervised remains largely a demo genre, and the reason is not capability, it is accountability, a point Amazon itself underlined by instituting mandatory peer review for AI-initiated production changes after learning the alternative firsthand.
That safeguard is the tell for where this settles. The industry is converging not on autonomous operators but on prolific junior colleagues: systems that produce unlimited drafts and hold no pager. Every keynote promise gets filtered, eventually, through the question of who gets paged, and the answer keeps coming back human. The reason autonomy stalls at the pager is the same one a playable trolley problem makes visceral: an agent under moral pressure is exactly what nobody wants operating unsupervised.
The builder's read: budget for the assistant, staff for the review. The bottleneck has moved from writing changes to absorbing them, and the December keynotes did not mention that part, because absorption does not demo well.