Play 54
AI Customer Support v2
Multi-channel support with sentiment routing and automated resolution.
Multi-channel AI customer support platform with ticket classification, sentiment-aware routing, and knowledge base search via RAG. Automates resolution for common issues while escalating complex cases through configurable workflows. Features CSAT prediction, real-time agent assist, and integration with Azure Communication Services for omnichannel engagement across chat, email, and voice.
Architecture Pattern
Multi-channel RAG: sentiment-aware routing, auto-resolution, escalation workflows
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Support Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (226 lines), evaluate (125 lines), tune (177 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + AI Search inputs + envFile
TuneKit (AI Config)
- config/openai.json — empathetic tone, resolution accuracy
- config/guardrails.json — escalation thresholds, safety filters
- evaluation/eval.py — Resolution rate >70%, CSAT >85%
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.