Human approval

Jakob Nielsen, a usability researcher, argues that people approving an AI agent's actions stop paying attention, and that products should ask less often and offer undo.

Dropbox's engineers sent every AI agent change in Reclaim, their calendar assistant, through the same checks of scheduling rules that people's changes pass, and let users preview it first.

Agoda, the online travel company, surveyed developers in Southeast Asia and India: 53 percent use AI agents widely, and 79 percent require a person to approve production deployments.

Rama Lingamgunta, who builds AI agent platforms, replaced a single Approve button with three earlier approvals after a reviewer passed a 1,400-line agent change in under two minutes.

A designer fixed a billing problem for clinicians in an afternoon with an AI coding agent, and his design lead used the review to take it from good to great.

Addy Osmani withdraws his advice to read every line of AI-written code and proposes automated review of every change, human review matched to risk, and a person approving every merge.

Microsoft reports that staff in its Europe South region now take up AI agents without being pushed, and that the hard part has moved to governing them.

Cursor launched two AI bots for the work after a code change is proposed: one plans and watches the release, and one reviews every change for security flaws.

Warp, which makes tools for software teams, lets the person who asked its AI agent for a code change review that change, instead of waiting for a separate reviewer.

At Bolt, designers now build interface components with AI agents directly in the library that ships, and engineers review those components instead of rebuilding them.

When designers at Leonardo De La Rocha's company began making code changes with AI agents, the review broke down, so he set out who reviews them and to what standard.

Pavel Samsonov argues that treating an AI model as a colleague lets people hand over work nobody has checked, and that whoever hands it over stays responsible for it.

A GitHub developer advocate argues that people must still review code written by AI, with effort matched to the risk, until they can explain and own the result.

Ananya Das, an intern at DataHub, tested a support agent before its release and found that an unchecked human review had made the agent look worse than it was.

Gergely Orosz describes how OpenAI builds software with its coding agent Codex: people define the problem, agents write and review the code, and high-risk changes can require a person's review.

Delphi, a company with ten engineers, ships to production over 100 times a day and first sees its AI agents' work on live preview links, according to Vercel.

Raluca Budiu, an editor at Nielsen Norman Group, explains that the firm uses AI to write and critique articles, but only a human expert decides whether it publishes them.