Authority Gradient
A No-Cost Way For The AI To Disagree
An AI built to comply will carry out a clear-but-wrong instruction it could see was wrong. The move: wire a structured push-back the AI can raise at zero cost — it flags a reason category and a detail, you pick revise, override, or cancel, and the exchange is logged. Unlike a clarifying question, this fires after the instruction is clear but its content conflicts with something the AI can see. (The no-cost two-challenge rule comes from aviation Crew Resource Management.)
Framing
The problem
An AI built to follow instructions will execute a clear-but-wrong one even when it can see the conflict — it has no first-class way to say so without sounding like it is refusing.
The pattern
Give the AI a structured push-back it can raise at no cost: it flags a reason category and detail, you pick revise / override / cancel from a menu, and the exchange is logged as calibration data.
Why chat breaks here
Chat turns disagreement into awkward prose — the AI complies silently or wraps a concern in hedging you click through; there is no first-class action that makes raising it free and resolving it structured.
Risks
Push-back on routine work becomes argumentative AI, so gate it by stakes; and without a genuine no-cost guarantee plus a logged audit trail, the affordance is theatre — the same Crew Resource Management lesson aviation learned the hard way.
Avoid when
The work is open-ended or creative and the user wants a yes-and partner — or this is a clarifying question that should fire before the AI guesses (that is Disambiguation Branch), not a push-back after a clear instruction.
Use when
A logged push-back action turns a concern the AI can already see into a decision you get to make, instead of an error you find afterward.
DOPE evaluation
- Directability
- The delegatee can interrupt to challenge; the delegator picks revise / override / cancel from a structured menu, not from prose
- Observability
- Every push-back instance is visible — reason category, detail, resolution. The system makes disagreement legible, not awkward
- Predictability
- Push-back always costs the lower-authority party zero — by contract, not by social signal
- Explainability
- Each challenge is logged with reason category and outcome, creating calibration data for both parties over time
Closest neighbours
- Aviation · Crew Resource Management (CRM) (ICAO / FAA) — The reference implementation. After a string of crashes attributed to too-steep authority gradients between captain and first officer, the aviation industry codified Crew Resource Management — explicit two-challenge rule, mandated checklists, no-penalty push-back culture. Trained, audited, mandatory.
- WHO · Surgical Safety Checklist (World Health Organization) — Three-stage pre-/intra-/post-op checklist that mandates the most-junior team member voice concerns. Cut surgical mortality by ~47% in pilot studies. Authority gradient flattened by protocol, not by personality.
- Anthropic · Constitutional Classifiers (Anthropic) — A separate classifier system runs alongside the generator in production and can block or flag its outputs against a constitution (cut universal-jailbreak success from 86% to 4.4%). A live second system that outranks the first on safety grounds — the closest shipped authority gradient in the AI stack.
- GitHub · CODEOWNERS + required reviewers (GitHub) — For sensitive code paths, a required reviewer with explicit domain authority must sign off. The PR author and reviewer occupy known positions on the authority gradient, and the system enforces the gap. Closest software-engineering analogue.
FAQ
When should I use the Authority Gradient pattern?
A logged push-back action turns a concern the AI can already see into a decision you get to make, instead of an error you find afterward.
When should I avoid the Authority Gradient pattern?
The work is open-ended or creative and the user wants a yes-and partner — or this is a clarifying question that should fire before the AI guesses (that is Disambiguation Branch), not a push-back after a clear instruction.
What problem does Authority Gradient solve?
An AI built to follow instructions will execute a clear-but-wrong one even when it can see the conflict — it has no first-class way to say so without sounding like it is refusing.
Why is chat the wrong fit for this?
Chat turns disagreement into awkward prose — the AI complies silently or wraps a concern in hedging you click through; there is no first-class action that makes raising it free and resolving it structured.
Related patterns
- Often paired with: Autonomy Dial — Autonomy Dial sets what the agent is allowed to do (top-down policy). Authority Gradient sets whether the agent is allowed to disagree (bottom-up affordance). Two halves of the same question — set them both or get sycophancy by accident.
- Often paired with: Cognitive Friction — Friction scales with stakes; push-back scales with how dangerous compliance would be. Compose them — let routine actions flow, let high-stakes ones earn challenges.
- Often paired with: Feedback Loop — Each push-back instance is a structured feedback signal — the gradient produces calibration data that flows back into the loop.