Skip to main content

The Building Blocks

Velatir is built around a small set of concepts. Once these click, the rest of the platform follows.

Organisation & workspaces

Your organisation is the top-level account. Workspaces sit inside it and separate activity by team, department, or project.

Sessions & traces

Every AI interaction is captured as a trace. Related traces are grouped into a session that represents a complete conversation or workflow.

Agents

Gatekeeper and Data Protector review every trace. Gatekeeper controls which services can be used, and Data Protector catches sensitive content.

Assessments

Each agent records an assessment for every trace it reviews, with the verdict and the reasoning behind it.

Instructions

Your own rules that tell an agent what to do in a specific scenario, such as always blocking a project codename.

Insights

Aggregated views of how your organisation uses AI, where activity concentrates, and what agents are catching.

How They Fit Together

A trace is captured

The browser extension or desktop app sends an AI interaction to Velatir as a trace. Each trace has a direction: Inlet (a request to an AI service), Response (a reply from it), or Signal (an event). Related traces are grouped into a session.

Agents assess it

Your active agents review the trace at the same time. Each one records an assessment and reaches a verdict, applying your categories and instructions.

The outcome is resolved

The verdict depends on each agent’s role. An Observer flags its findings for review. An Enforcer can block the trace or escalate it for approval. The most restrictive outcome wins.

People are notified

If a trace is escalated, it is sent to your connected channels so the right people can respond.

Everything is logged

The trace, each assessment, and the outcome are recorded for audit purposes.

Key Principles

Traces are the foundation

Every AI interaction is captured as a trace. This gives your organisation full visibility into AI usage.

Agents handle the volume

Agents review every trace automatically. People only see what an agent flags or escalates.

Roles control authority

Each agent runs as an Observer or an Enforcer. You can start with monitoring only and add enforcement as you build confidence.

Instructions tune behaviour

Instructions let you teach an agent how to treat a specific scenario, so its verdicts match your organisation over time.

Everything is auditable

Every trace, assessment, decision, and outcome is logged with full context. Your compliance trail is always complete.

Organisation and Workspaces

ConceptDescription
OrganisationYour company account. Holds members, settings, agent defaults, and your subscription.
WorkspaceA space within your organisation for a team, department, or project. Workspaces can nest, and each has its own activity.
Organisation rolesAdministrator (full access) and Reader (view only).
Workspace rolesAdmin, Editor, and Reader, with progressively fewer permissions.
See Roles & permissions for the full breakdown.

Trace Directions

DirectionDescriptionExample
InletA request going to an AI serviceSomeone submits a prompt to a chat assistant
ResponseA reply coming back from an AI serviceThe assistant’s answer
SignalA related eventA session starting, or a background event

Assessment Outcomes

OutcomeWhat it means
AllowedThe agent had no concern. The trace proceeds.
FlaggedAn Observer noted a finding for review, without blocking.
BlockedAn Enforcer stopped the trace.
EscalatedThe trace was sent to a person for review or approval.

Understanding agents

Meet Gatekeeper and Data Protector.

Trace lifecycle

Follow a trace from capture to final state.