AI agents, MCP servers and RAG that run in production
I build AI that works on real operational data: tool use into live systems, retrieval with evals, and the boring reliability work that keeps it safe.
Production AI agent
Built on the Anthropic and OpenAI APIs with LangChain. It plans, calls tools, keeps memory and runs every action through guardrails.
Tool server for LLMs
Structured query and action tools with secure calls into the database, telemetry and internal services.
Qdrant + evals
SageMaker · Bedrock
Ask my CV
Grounded in this site's case studies and CV, with sources.
Ask me anything about Ahmed's projects, stack or availability.
What AI systems has Ahmed Mamdouh shipped to production?
Does he do fine-tuning?
Can he add AI to an existing product?
The AI stack I use
AI and real-time case studies
Real-time device platform
A device management backend that keeps 100,000+ devices connected at once. The product is under NDA, so this page covers the engineering, not the product.
Read case studyAI agent + MCP server
A production AI agent with tool use and guardrails, plus an MCP server that lets LLM clients query and act on internal systems under strict rules.
Read case studyAdd an AI agent to your product
Tool use, RAG on your data, guardrails and evals — scoped in one call.