AI Solutions Architect | Azure, MuleSoft & API Management Specialist
Building intelligent systems at the intersection of AI, cloud infrastructure, and enterprise integration.
I design and build AI-powered applications on Azure and MuleSoft, with deep expertise in API Management, AI agents, and MCP (Model Context Protocol) integrations. My work focuses on making AI practical and production-ready for enterprise environments.
Projects I built from scratch.
 Agent + MCP |
snow-meta-tool ServiceNow MCP meta-tool — 3 generic tools (discover, query, write) with per-user identity propagation via Azure APIM JWT Bearer OBO flow    
|
 Agent + MCP |
salesforce-meta-tool-identity-propagation Meta-tool MCP server for Salesforce with cross-cloud identity propagation — AI agents manage Salesforce resources using the caller's Azure identity end-to-end 
|
|
Agent + MCP |
propagate-id-entra End-to-end Entra ID identity propagation from browser through AI Foundry agents and APIM to backend APIs — no service accounts in the data path  
|
 Agent |
simple-order-agent Order processing agent using Claude SDK, MuleSoft MCP, and A2A protocol    
|
|
MCP |
azure-apim-mcp-server MCP server for Azure API Management — manage APIs through natural language 
|
|
AI App |
ai-avatar-presenter AI-powered avatar presentation assistant — upload PowerPoint slides and have an AI avatar present them with multilingual TTS, interactive Q&A, and Teams integration    
|
Identity propagation patterns — see full project descriptions in AI Agents & MCP above.
| Project | Security Pattern |
|---|---|
| snow-meta-tool | JWT Bearer OBO flow — Azure APIM exchanges Azure AD token for ServiceNow per-user token |
| salesforce-meta-tool-identity-propagation | Cross-cloud identity: Azure AD → APIM → Salesforce via On-Behalf-Of JWT Bearer |
| propagate-id-entra | Entra ID token passthrough from MSAL.js SPA through AI Foundry + APIM to backend API |
|
Learn |
anthropic-academy Worked examples from the Anthropic Academy curriculum 
|
|
Fork+ |
get-started-with-ai-agents
· forked from Azure-Samples My additions: AI Foundry endpoint & A2A documentation (1 400+ lines), Bicep infra customizations, extended README 
|
Unmodified forks kept for learning and workshops.
| Project | Upstream | Purpose | |
|---|---|---|---|
|
get-started-with-ai-chat | Azure-Samples | Azure AI Foundry chat application reference |
|
voicelive-api-salescoach | Azure-Samples | AI-powered voice training for sales with Azure Voice Live API |
 |
TechWorkshop-L300-AI-Apps-and-agents | Microsoft | L300-level AI workshop material |
|
prompt-eng-interactive-tutorial | Anthropic | Interactive prompt engineering exercises |
 |
karpathy-autoresearch | karpathy | Autonomous AI agent running LLM training experiments |
Enterprise identity propagation patterns for multi-cloud AI agent architectures — making every AI action traceable to the real user across Azure, Salesforce, and ServiceNow.
All repositories follow a standard convention for working with AI code agents:
AGENT.md— public project instructions, architecture, and conventions committed to each repo.claude/— private per-project configuration, lessons learned, and session context (gitignored)- Global workflow rules — verification standards, subagent strategy, and self-improvement loop loaded across all projects
This separation keeps project knowledge accessible to collaborators while keeping iterative agent context private.
| Doc | What's inside | |
|---|---|---|
| 🤖 | AI Agents & Apps | Architecture, stack details, and fork modifications |
| 📚 | Learning Resources | Curated tutorials, courses, and reference links |
| 🔐 | Security Projects | Identity propagation patterns and API security |
Currently exploring enterprise identity propagation patterns for multi-cloud AI agent architectures.