Skip to main content

AI in Resolve

Resolve uses AI in two distinct ways, and it is worth separating them because the risks differ.

Configuration generatorsOperational AI
DoesDrafts settings for you to reviewActs on live tickets
RunsWhen you press a buttonContinuously
RiskA bad draft you can editA wrong answer reaching a customer
WhereFive settings screensRunbooks, deflection, the assistant

1. The five configuration generators​

Each drafts a starting configuration you then edit. Nothing is saved until you accept it.

GeneratorWherePermission
Generate WorkflowStatuses & WorkflowsCreate Service Desk Status and Workflow with AI
Generate Custom FieldsCustom FieldsCreate Service Desk Custom Fields with AI
Generate Service CatalogService CatalogCreate Service Desk Catalogue with AI
Generate ClassificationTicket ClassificationCreate classification with AI
Generate Release StagesRelease BoardCreate Service Desk Release flow with AI
Use them on new projects, not to change live ones

Their value is escaping the empty screen. On a project already carrying tickets, a generated workflow or taxonomy replaces structure that live records depend on. Generate early; edit by hand later.

A generator is a proposal, and it does not know your business

It produces a plausible, conventional configuration. Plausible is not correct — it cannot know that your Pending status must pause the SLA clock, or that a laptop request needs three approvals. Review every field, especially the Pause SLA flags.


2. Operational AI​

FeatureWhat it does
AI RunbooksStanding diagnostic and action steps per intent
AI training sourcesThe corpus the assistant answers from
Ticket deflectionSuggests articles while a customer writes a ticket
Deep TranslateTranslates content, respecting the glossary
The corpus decides the answers

Operational AI answers from what you ingested. An outdated document makes it confidently wrong — worse than having no answer, because it will be believed. Curate training sources and check chunk counts after ingestion.


3. Cost and governance​

Every AI call consumes credits. AI Governance (/org/resolve/ai-governance) reports daily calls, spend by model and by utility, tokens, and failures.

Failures still cost

The governance view separates Calls, Credits, Tokens and Failed. A rising failure count with steady spend usually means a misconfigured utility retrying — worth checking before it becomes a bill.


4. Don't confuse these​

These twoDiffer by
Generate with AI vs AI RunbooksOne-off configuration drafting vs standing operational instructions
AI training sources vs KB articlesWhat the AI reads vs what customers read
AI Governance vs Integration TelemetryAI spend vs API traffic