ai-in-production

A plan engine for dynamic planning and reliable execution of AI agent workflows.

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18 graded queries, zero API calls.

Guide: from fragile multi-agent app to prod ready with orra - code and resources.

Using celery framework with AI models (Documentation)

Public profile README covering how I approach product, AI systems, and customer signal in production.

A hands-on course repository for Evaluating AI Agents, created with Arize AI, that teaches you how to systematically evaluate, debug, and improve AI agents using observability tools, structured experiments, and reliable metrics. Learn production-grade techniques to enhance agent performance during development and after deployment.

Serviço de RAG sobre atas do Copom + boletim Focus, servido como API (FastAPI+Docker), com eval harness (golden set, LLM-as-judge, gate de CI) e observability de custo/latência/tokens por request.

NexusFleet AMR: Autonomous Fleet Orchestrator & Self-Healing Warehouse Digital Twin. Space-Time Multi-Agent Path Finding (MAPF), Chaos Engineering, Executive BI, and HITL AI Copilot (FastAPI + React 19 + Cloud Run).

IBM AI Enterprise Workflow Specialization

How a physician and a set of AI agents run a company together. Patterns, review gates, and the mistakes we wrote down.

Data warehouse de indicadores macro brasileiros orquestrado com Airflow, modelado em camadas raw→staging→gold via dbt, com agente text-to-SQL seguro para consulta em linguagem natural.

Personal site of Khaqan Shaheen, Head of IT in Dubai: Odoo ERP and AI in daily production