Play 10
Content Moderation
Filter harmful content with Azure Content Safety and APIM gateway.
Every AI response passes through Azure Content Safety for severity scoring across hate, violence, self-harm, and sexual categories. APIM acts as the gateway, enforcing rate limits and routing. Custom blocklists catch domain-specific terms. Azure Functions handle async processing for high-volume scenarios.
Architecture Pattern
Safety gateway, severity scoring, blocklists, custom categories
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Content Mod Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (121 lines), evaluate (101 lines), tune (120 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with Content Safety key + envFile
TuneKit (AI Config)
- config/safety.json — severity levels, custom categories, blocklists
- config/guardrails.json — filtering rules, thresholds
- evaluation/ — moderation test sets
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.