Play 64
AI Sales Assistant
Medium✅ Ready
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
Azure OpenAICosmos DBMicrosoft GraphAzure AI SearchAzure Functions
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
Lead score thresholdPersona temperatureEmail tone profileForecast confidence levelRAG chunk size
Estimated Cost
Dev/Test
$60–120/mo
Production
$1.5K–5K/mo