Play 64
AI Sales Assistant
AI sales enablement with CRM integration, lead scoring, and personalized outreach.
Full-stack AI sales assistant that integrates with CRM via Microsoft Graph, scores leads using behavioral signals, drafts personalized emails, generates meeting preparation briefs, and produces pipeline forecasts with confidence intervals. Azure AI Search powers competitive intelligence retrieval, while Cosmos DB maintains conversation history and deal context. Provides deal risk analysis and next-best-action recommendations.
Architecture Pattern
RAG-powered conversational agent: CRM integration, lead scoring, sales workflows
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Sales Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (224 lines), evaluate (101 lines), tune (177 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI key input + envFile
TuneKit (AI Config)
- config/openai.json — gpt-4o for drafting, mini for scoring
- config/guardrails.json — tone guidelines, data access controls
- evaluation/eval.py — Lead accuracy >80%, Email engagement >25%
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.