Skip to content
← Back to Guide AutoServa Glossary

GuluStock and AutoServa · GuluStock and AutoServa: User Guide

AutoServa Glossary

VYROX Wiki · Updated 17 November 2026 · https://www.vyrox.com/wiki/autoserva-glossary

This AutoServa glossary explains the words used in a working session, in plain language. AutoServa is VYROX's service for running an agentic AI operator on a business queue. It is written for business owners, managers and risk or compliance colleagues.

How AutoServa Works

TermMeaning
OperatorThe tuned AI that works one of your queues, in the position of an operations staff member between your business and its systems
Decision FrameworkA written structure of inputs, thresholds, constraints, approvals and escalation. The main output of a decision audit
ThresholdThe value at which an answer changes, such as a tolerance percentage or a spending limit
Escalation RuleWhen a case stops being routine and must go to a person. Set per workflow, not guessed by the AI
PrecedentWhat you decided last time, kept searchable
QueueThe stream of repeating work one engagement targets, one queue at a time
Shadow RunningThe operator works live cases but nothing it produces is acted on, so accuracy can be measured first
Disagreement LogEvery case where the operator and a person differed, reviewed weekly

Governance

TermMeaning
Workflow GuardChecks every action against approval chains, spending ceilings, access scope, segregation of duties, retention rules and regulatory obligations before it runs
Evidence TrailWhat was read, which rule applied, which threshold was hit, which precedent it followed and who approved
Human in the LoopA person approves before anything irreversible is final
Segregation of DutiesThe preparer and the approver are different parties
Least PrivilegeOnly the access a role needs. The operator starts read-only
Data ResidencyA rule that data stays in a country or region
Air-GappedA system with no outside network connection, the strictest local deployment

AI Terms

TermMeaning
Agentic AIAI that plans steps and acts toward a goal, rather than answering one question at a time
Frontier ModelThe most capable model a provider offers now
Open-Weight ModelA model you can run on your own hardware
Fine-TuningExtra training on your documents, decisions and vocabulary
RAGRetrieval-augmented generation: fetch the passages a case needs from your documents before the model answers
EmbeddingA numeric form of text that finds similar meaning, not only matching words
Knowledge GraphYour framework held as connected entities and rules, such as vendor, contract, clause and precedent
Reasoning TraceThe path the operator took to an answer, kept with the evidence
HallucinationA confident statement that is false

Engagement Terms

  • Decision Audit: the first stage, two to three weeks, ending in a written framework you keep.
  • Codify: the stage where tacit judgement becomes an explicit document.

Frequently Asked Questions

What Is the Difference Between the Operator and a Chatbot?

A chatbot answers questions. The operator works a queue, acts inside your systems under your rules, and shows evidence.

Does Shadow Running Change Anything in Our Systems?

No. Nothing the operator produces is acted on during shadow running.

Related Guides

  • AutoServa Overview
  • AutoServa Worked Examples
  • Getting Started With AutoServa