Automatic by default#
Routing a ticket, gating an agent's tool call, checking an invoice against its order, moderating a post: set a threshold once, act on every answer above it, and take the safe path below it. Nothing has to wait for a person. The examples in these docs and in the playground are all of this kind.
Decisions about people#
A few areas are different. When DecisionNode helps make a consequential decision about a person in one of the categories below, a qualified person must review each decision before it takes effect. The answer can rank, flag and prepare the case; a person with the competence and the authority to change the outcome signs it off.
| Category | For example |
|---|---|
| Hiring | Screening, ranking or rejecting candidates, promotion and dismissal |
| Credit | Approving, pricing or limiting a loan or a credit line |
| Housing | Accepting or refusing a tenant, setting a deposit |
| Insurance | Accepting a policy holder, pricing a premium, settling a claim |
| Education | Admissions, grading that affects progression, discipline |
| Benefits | Granting, reducing or stopping public or private benefits |
| Law enforcement | Anything that leads to a stop, a search, a charge or a sentence |
| Health | Diagnosis, treatment, triage and access to care |
- Never on a protected trait. Do not ask DecisionNode to treat a person less favourably because of race, religion, sex, disability or another characteristic the policy lists. An attribute the decision genuinely depends on, such as income for a loan, is allowed where the law allows it.
- No inferring sensitive traits such as health, religion or sexual orientation without the person's explicit consent or a legal basis.
- Follow the law of your use case. Anti-discrimination, consumer protection, data protection and AI law (including the EU AI Act) apply to what you build; meeting them is your responsibility.
The safety check#
Every request to the hosted API is checked and, unless it is refused, answered. The check gives two calibrated probabilities: harm, that the request asks to choose, rank or target people to be hurt or killed, or to choose whom to harm by a protected attribute; and self_harm, that it seeks help to hurt oneself. Both come back on every response in the x-decisionnode-safety header, and in the body when you ask for them.
- By default the check only flags: both probabilities come back in the header and the request is answered.
- Stricter blocking is set per customer: flag or refuse either category at a threshold you choose. It can never be looser, and the self-harm check can never be switched off.
- A refusal is
403with{"detail": {"error_type": "refusal_error", "message": "...", "category": "self_harm"}}and no answers. It is not billed, and the same request is refused again. - As answers. With the request header
x-decisionnode-refusals: per-question, a refused request on/v1/decidecomes back as a200with a refusal answer for every question instead of the403. - Detection is never refused. Asking whether a message shows a risk of self-harm, whether a post is a threat or whether a payment is fraud is answered as usual, and we encourage it.
Safety check has the header, the opt-in body, key policies and code; Errors has the refusal.
Military use#
Military use is not allowed under the standard terms. It is available only under a signed Defence Contract Addendum, which defence and security bodies of the member states of the North Atlantic Treaty Organization, the member states of the European Union, Australia, Japan, New Zealand and the Republic of Korea (and their contractors) may sign. Even under the addendum some uses stay forbidden in every case, including targeting people by a protected trait or targeting civilians, any weapon of mass destruction, and any decision to use force without a responsible person's authorisation.
Report misuse#
If you see DecisionNode used in a way these rules forbid, write to abuse@bynn.com. Security issues go to security@bynn.com.