Concepts glossary

Definitions for the terms the rest of the docs assume you understand, in alphabetical order. Where a concept has its own guide, the entry links to it.

Activity — The running record of meaningful events in a project or across your organisation — documents added, analyses created, agents run. See Collaborating with your team.

Adoption — Your project’s own instance of an enabled framework. Enabling a framework in a project creates an adoption you evidence and assess against; the same framework adopted in two projects stays independent. See Working with frameworks.

Agent — A reusable AI assistant configured once and pointed at compliance work repeatedly. Built-in (system) agents are managed by Regnora; custom agents are the ones you build. See Building custom agents.

Agent database — An agent’s own structured store, which it reads and writes across runs so a recurring automation builds on previous work. Shown as a read-only preview. See Agent outputs.

Annex — A structural part of some standards (for example, ISO 27001’s Annex A), represented in a framework’s requirement tree.

Assessment — The result of the AI evaluating one requirement against your evidence during a gap analysis: a verdict, the reasoning, and the evidence it relied on.

Attestation — Marking an assessment as reviewed and correct. Attesting (or reverting) is how a human signs off on the AI’s verdict. See Running a gap analysis.

Automation — An agent wired to a trigger so it runs on its own. See Triggers & schedules.

Canvas — A rendered artifact an agent produces during a run — markdown with charts and tables — that you open and read. See Agent outputs.

Capability — Something an agent is allowed to do when it runs (read documents, write documents, web search, send email, and more). An agent has none until you grant them. See Building custom agents.

Catalogue — The central library of frameworks Regnora supports, which you browse and enable from. See Working with frameworks.

Checklist template — A reusable assessment plan — sections, checks, and assessor guidance — that you apply when planning a gap analysis to start from a known baseline. See Templates.

Clause — An individual requirement within a framework’s structure (the level standards typically frame as obligations).

Contributor — A seat that lets a member run gap analyses and spend credits, assigned independently of their role. See Members, roles & permissions.

Control — A specific safeguard or requirement within a framework, assessed during a gap analysis.

Directory — A folder for organising documents within a project. Directories help you navigate; they don’t change how the AI searches. See Managing documents.

Discover — A beta tool that generates an interactive visualisation of your project’s documents from a question you ask. See Discovering your documentation.

Discussion — A project’s comment thread for project-level conversation, with one level of replies and a resolve flow. See Collaborating with your team.

Document — A piece of evidence you upload — a policy, procedure, or record. Regnora indexes its text for semantic search. See Managing documents.

Document package — A curated bundle of document templates you can copy into a project together. See Templates.

Document state — Where a document is in its lifecycle: staged (proposed, awaiting a decision), draft, active (live evidence), or archived. See Managing documents.

Evidence — The documents in a project that a gap analysis assesses against and agents read.

Framework — The standard or regulation you work against (ISO 27001, ISO 9001, GDPR), held centrally as its full set of requirements. See Working with frameworks.

Gap analysis — Regnora’s flagship workflow: the AI assesses every requirement of an enabled framework against your evidence and you review the verdicts. See Running a gap analysis.

Guest — Someone from outside your organisation invited to a single project, who sees only that project. See Members, roles & permissions.

Instructions — The markdown that defines a custom agent’s behaviour — its system prompt. Versioned with a draft/published lifecycle. See Building custom agents.

Member — A person in your organisation, with an organisation role. See Members, roles & permissions.

Memory — Persistent know-how in the Library that agents recall between runs; the agent proposes changes and your team accepts them. See Skills, rules & memories.

Multi-factor authentication (MFA) — A second sign-in factor from an authenticator app. Members set it up for themselves; owners and admins can enforce it organisation-wide. See Organisation settings & security.

N/A — A gap-analysis verdict meaning the requirement does not apply to the scope.

Organisation — The top-level container for your projects, members, and billing.

Output — What an agent produces — a document, a revision, a canvas, or an email — recorded in the agent’s Outputs and proposed for your approval. See Building custom agents.

Pass — A gap-analysis verdict meaning the evidence satisfies the requirement.

Project — The primary unit of scope; every document, framework, and analysis lives in one. Internal projects are your own work; external projects are client or auditor engagements. See Setting up a project.

Project access — Whether a person can reach a project. Organisation owners and admins reach every project automatically; others are added explicitly. Access is granted, not graded into project-specific roles. See Members, roles & permissions.

Project profile — A project’s organisation attributes that agents read to tailor their work. See Project profile & context.

Requirement — An individual obligation within a framework (a clause, control, or article) that a gap analysis assesses.

Revise — The AI flow for drafting and improving documents, with every change staged for review. See Drafting & revising documents.

Revision — A set of staged document changes an agent or the Revise flow produces, which you apply or discard. See Drafting & revising documents.

Role — A member’s organisation-level permission level: Owner, Admin, Member, or Viewer. See Members, roles & permissions.

Rule — An always-on instruction the agent must follow every run, authored by your team and not changeable by the agent. See Skills, rules & memories.

Run — One execution of a gap analysis (or an agent). A gap analysis can have several runs; re-assessing produces fresh verdicts without losing history. See Running a gap analysis.

Sign-in (single sign-on) — Signing in with an existing Google or Microsoft account instead of an email link. See Organisation settings & security.

Skill — Reusable AI guidance in the Library, layered onto an agent’s system prompt and chosen per agent. See Skills, rules & memories.

Stage — One of the four phases of a gap analysis: Plan, Analyze, Review, Act. See Running a gap analysis.

Staged change — A change an agent proposes that sits in a staged state until you approve it, at which point it becomes live.

Submission — A request to add a framework that isn’t in the catalogue yet, which Regnora processes before it becomes enableable. See Working with frameworks.

Template — A reusable starting point in the Library: document templates (ready-made documents) and checklist templates (reusable assessment plans). See Templates.

Trigger — What fires an automation: a schedule, a document event, or an inbound email. See Triggers & schedules.

Verdict — The outcome the AI assigns a requirement in a gap analysis: Pass, Gap, or N/A.

Version — A point-in-time snapshot. Documents are versioned (re-uploading creates a new version), as are agent instructions (published as v1, v2, …).