AI Closure and ITAMation
Structured ticket close for GLPI 11 — with optional AI assist and governed asset updates
Turn closure from a flat dropdown into service intelligence: enforced taxonomy, constrained AI suggestions, propose-then-approve ITAM, and draft knowledge articles — without changing GLPI core.
AI Closure and ITAMation is an optional Echo-9 plugin for GLPI 11.0.0 and later. It is typically delivered with an Echo-9 GLPI subscription or implementation. Run models on-premises with Sovereign AI so PII-redacted analysis never leaves your network.
What is AI Closure and ITAMation?
Native GLPI solution types are flat. Teams cannot reliably report why tickets closed, which root causes dominate, or which hardware outcomes were scrap versus repair. Quality often collapses at the exact moment the organisation most needs clean data.
This plugin makes ticket close the control point for quality, assets, knowledge and AI governance. Every solution can carry a primary → secondary → optional root cause classification that is consistent, reportable and entity-aware. Enforcement runs in PHP — even when AI is offline.
Product principle: AI assists. Rules enforce. Humans approve irreversible automation.
What You Get
Multi-tier taxonomy
Primary, secondary and root-cause codes with admin CRUD, seed catalogue and entity-aware visibility
Enforcement without AI
Dependent dropdowns, minimum solution length and category rules — validation never depends on a model
Constrained AI assist
Optional Analyze with AI on the solution form. Suggestions must pick from live taxonomy IDs, not invented labels
Sovereign-first inference
Default path is local Ollama. Cloud OpenAI and compatible gateways are opt-in, with PII redacted before any call
Propose-then-approve ITAM
Closure codes can queue asset actions such as pending disposal or return to stock. Assets change only after approve
Draft-only knowledge
Eligible closed tickets become draft knowledge articles. Humans publish — AI never auto-publishes
How You Roll It Out
Feature flags default off for AI, ITAM and knowledge. Enable capability in stages.
1. Taxonomy first
Load or edit closure codes and turn on enforcement. Quality improves with no model required.
2. AI when ready
Point the plugin at Sovereign AI or an approved gateway. Technicians still confirm what is saved.
3. ITAM proposals
Map codes to pending asset actions. Approvers see a before/after preview, then apply or reject.
4. Knowledge capture
Enable draft article synthesis once eligibility and PII policy are agreed.
Built for Trust
The plugin does not auto-close tickets from AI output, auto-publish knowledge, or auto-apply irreversible ITAM changes unless an explicit high-privilege flag is enabled (off by default). API keys are encrypted at rest. Audits retain model, confidence and outcomes with configurable retention.
Requires GLPI 11. Licensed GPLv3+.