Play 05
IT Ticket Resolution
Auto-classify, route, and resolve IT tickets with event-driven AI.
Incoming tickets hit Service Bus, Logic Apps triggers classification via GPT-4o-mini (cheaper, fast enough for triage), the agent routes to the right team or auto-resolves known issues. ServiceNow MCP connector syncs state. Event-driven architecture means it scales to zero when idle.
Architecture Pattern
Event-driven async automation, ITSM integration
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — IT Ticket Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (106 lines), evaluate (109 lines), tune (104 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + ServiceNow keys + envFile
TuneKit (AI Config)
- config/openai.json — gpt-4o-mini for cost efficiency
- config/agents.json — routing rules, confidence thresholds
- config/guardrails.json — escalation criteria
- evaluation/test-set.jsonl — 50 ticket samples
Tuning Parameters
Machine evidence
FrootAI evidence lifecycle
This is an internal evidence maturity label, not third-party certification, accreditation, legal compliance, or a production guarantee. Missing or expired evidence demotes automatically; catalog claims cannot promote a play.
This play currently has design evidence only. A runnable scenario, endpoint evaluation, and build receipts are the next contiguous gates.
Repo Intelligence
v1A no-clone, revision-pinned map for agents and humans. Observed evidence is separated from inferred flow so the output stays useful without pretending to be a full call graph.