Normis
Normis is a deterministic compliance API for AI agents, providing real-time, rule-cited, auditable decisions.
Last updated September 1, 2026
Overview
Normis is a compliance API for AI agents. It provides real-time, rule-cited, auditable decisions for regulated actions. Before an agent takes a regulated action, it calls POST /v1/check and receives a decision — allowed, blocked, or escalate — together with every rule it evaluated, each carrying its own outcome, version, and the legal source it cites. Normis is not a model and does not predict; interpretation of the law happens offline, in advance, and a lawyer signs each rule node. No language model runs in the Normis decision path, ensuring deterministic outcomes.
History
Normis is a compliance API for AI agents. It provides real-time, rule-cited, auditable decisions. The product is described as 'Compliance API for AI agents — real-time, rule-cited, auditable AI agents in regulated environments have no compliance layer — they guess. Normis is that layer: one API call before every regulated action returns allowed, blocked or escalate, with the exact rule cited.' The about page states: 'Normis is a deterministic compliance API for AI agents. Before an agent takes a regulated action, it calls POST /v1/check and receives a decision — allowed, blocked or escalate inside a covered jurisdiction — together with every rule it evaluated, each carrying its own outcome, version and the legal source it cites. Normis is not a model and does not predict. Interpretation of the law happens offline, in advance: each regulation is read and written down by hand as a structured rule node, and a lawyer signs it. At request time Normis only walks that rule graph in memory. No language model runs in the Normis decision path, which is why the same inputs always produce the same decision, and why the answer comes back in milliseconds rather than at the speed of a model call.'
Sources
Cite this profile: Cite the canonical profile. /brand-wiki/normis · Editorial policy · How profiles are compiled