Creative Technologist & AI Agent Developer

I design and build production-grade AI agent systems — from single-agent RAG pipelines to multi-agent orchestration frameworks. My work spans agentic workflow design, retrieval-augmented generation, prompt engineering, full-stack AI applications, enterprise AI architecture, and serverless deployment patterns. I also apply generative AI tools and prompt engineering techniques to produce commercial brand imagery for major retail clients.

Based in US & EU/Ireland.

🌐 paulforlando.com  |  💼 LinkedIn  |  📧 Available for freelance & consulting

Single Agents → Multi-Agent Systems → Enterprise Orchestration Pipelines → Full-Stack AI Applications → Serverless Production Systems

I focus on agents that are production-ready — properly configured, defensively prompted, and designed to fail gracefully. Not just demos.

Production-ready enterprise agentic AI on AWS

A fully functional travel booking agent demonstrating serverless multi-tool agent orchestration:

• Agent Framework: Strands SDK + Bedrock Nova Lite
• Memory: S3 SessionManager for persistent conversation history
• RAG: Bedrock Knowledge Bases for private data access
• Extensibility: Model Context Protocol (MCP) dynamic tool loading
• API: Secure HTTP via API Gateway + Cognito OAuth2
• Scale: Handles 1000+ concurrent requests, ~$0.02/request

Pattern: Multi-tool orchestration → Persistent memory → RAG integration → Secure API exposure

GitHub: serverless-agentic-ai-travel-agent

Stack: Strands SDK · Bedrock · Lambda · API Gateway · Cognito · S3 · Knowledge Bases

I use generative AI tools with prompt engineering techniques to produce brand imagery for major retail clients across the following disciplines:

• Generative AI Image Creation
• AI Art Direction
• Commercial Product Visualization
• Lifestyle Imagery

🔗 View Portfolio on ArtStation  |  Repository

Agent Design — tool routing, prompt engineering, multi-agent orchestration, supervisor patterns, retrieval-augmented generation, hallucination detection, moderation, memory, full-stack AI applications, MCP server development, serverless agent deployment

Cloud & Infrastructure — AWS Lambda, API Gateway, Bedrock, Cognito, S3, Knowledge Bases, CloudWatch, serverless architecture patterns

Stack — Flowise · LangChain · OpenAI API · Python · FastAPI · Next.js · n8n · TypeScript · OpenRouter · Exa · Postgres · FAISS · Neon · Supabase · Claude Code · Pinecone · FastMCP · MCP Protocol · Railway · Vercel · Strands SDK

Disciplines — 3D Visualization · Generative AI · Data Analytics · AI Product Visualization · Serverless Architecture

Every agent in this portfolio is built with the same standard:

• Explicit, rule-based system prompts — no vague instructions
• Tool descriptions written as policies, not labels
• Temperature tuned to the use case — not left at default
• Failure modes addressed — iteration caps, moderation, fallbacks
• Production considerations documented — memory, security, deployment

Every live application in this portfolio is built with production-grade security and cost controls — not just functional demos.

MCP Server Security Both custom MCP servers implement API key authentication (X-API-Key header, 401 on invalid key) and sliding-window rate limiting (5–10 requests/IP/hour, 429 on exceed) with self-host instructions embedded in every error response. Rate limiting is implemented as pure middleware without third-party auth frameworks — correct IP detection behind Railway's proxy via X-Forwarded-For header parsing.

AWS Lambda Security & Scalability The serverless agentic AI system implements Cognito OAuth2 authentication, per-user session isolation, S3-backed state management, and automatic horizontal scaling. Infrastructure costs are controlled through serverless pay-per-use pricing (~$0.02/request), with no idle server overhead.

Cost Protection All LLM API keys (OpenAI, OpenRouter) are capped at hard monthly spend limits. Exa AI auto-recharge is capped per calendar month. Rate limiting at the infrastructure layer provides the first line of defense; spend caps at the provider level provide a hard ceiling if rate limiting is ever bypassed.

Production AI systems require controls at every layer — request-level rate limiting, infrastructure-level authentication, provider-level spend caps, and cloud-native security. Each application in this portfolio is built with these standards, reflecting practices applied in enterprise deployments where cost, security, and reliability are non-negotiable.

Open to collaboration on agent design, AI workflow architecture, serverless AI systems, and creative technology projects.