Glossary
Terms used across Doram.
| Term | Meaning |
|---|---|
| ABAC | Attribute-based access control. Rules that decide which rows a person can see. |
| AI analyst | The agent your team asks questions. It reads facts only through the retriever and gets SQL only from the semantic compiler. |
| Approved | A trust level. Accepted by its owner, or approved automatically because the change is low risk. |
| Certified | The highest trust level. Signed off by its owner as the company's official definition. |
| Company second brain | The company's semantic context graph, and the agents that keep it current. |
| Context layer | The layer that holds how things connect, and why: joins, rules, policies, events and decisions. |
| Context pack | What the retriever returns: definitions, the join path, rules, policies, events and decisions, each with evidence. |
| Crawler agent | The only agent that creates drafts. It reads your systems and drafts facts from evidence. |
| Data-backed fact | A fact built on the database, such as a metric or a join, that can be tested against real data. |
| Discovered | The lowest trust level. Found by the crawler agent, with evidence, but not checked yet. |
| Evidence | The source behind a fact: a query, a model, a document, a tool record or a person. |
| Feedback agent | The agent that learns from how people use the analyst, and turns repeated signals into drafts. |
| Grain | The level a metric is counted at, such as one order line or one customer per month. |
| Graph version | One numbered state of the graph. Every change creates a new version. |
| Knowledge fact | A fact that can't be tested against data, such as a decision, a policy or an event. |
| Masked sample | A few example values from a column, with personal values hidden. |
| Monitoring agent | The agent that watches your sources for changes and checks what each change affects. |
| Ontology layer | The layer that holds what things are: entities, columns and the words people use for them. |
| Persona | A group of people with its own scope, such as Finance or Sales. |
| Question memory | Approved questions and how each one was resolved, used to answer similar questions. |
| RBAC | Role-based access control. Rules that decide which facts a role can see. |
| Read record | What Doram keeps for each answer: the graph version, the person, the question and the facts it used. |
| Replay | Running a metric or an answer again to check it still gives the same result. |
| Retriever | The only way to read the graph. It finds, ranks and resolves what a question needs. |
| Semantic compiler | The code that turns a context pack into one SQL query, with access rules applied. |
| Semantic context graph | The graph of nodes and edges that holds what your company knows about its data. |
| Semantic layer | The layer that holds how numbers are counted: metrics, and the ways to split them. |
| Slot | One part of a question: the metric, a split, a filter, the time range or the task. |
| Trust level | Discovered, validated, approved or certified. It decides whether a fact can be used in answers. |
| Validated | A trust level. A metric or join that ran on real data and matched a known result. |
| Workspace | One customer's own graph, evidence and settings, in the region it picked. |