Agentic AI · Data science · Palm Beach, FL
Twenty years of production engineering, now pointed at agent fleets, MCP servers, and calibrated data systems. I design them, build them, and run them — with evals and human gates, not vibes.
Get started
Services
Six practices that compose: agentic AI and MCP on top, data science and evals in the middle, twenty years of production infrastructure at the bottom.
Agent fleets with shared memory, MCP servers that expose your systems as tools, and human-approval gates on anything with side-effects. Agents that survive contact with production.
You get — a working agent wired to your real systems, with an off switch.
Explore agentic AI →RAG over private knowledge bases, local-first deployment on Ollama and llama.cpp, model selection with evals, and context engineering that keeps answers grounded.
You get — a model that knows your business and can prove it.
Explore LLM systems →Calibrated forecasting, behavior analytics, BI dashboards in Looker, Tableau, and Grafana, automated alerting, and metrics design — on a Cisco-certified data stack.
You get — numbers your board can lean on.
Explore data science →n8n pipelines with LLM steps, self-hosted marketing automation (Mautic plus AI), and process monitoring — the ops glue that keeps automations from rotting between runs.
You get — workflows that run themselves and report in.
Explore automation →Multi-region AWS with 99.99% documented uptime, HIPAA- and SOC II-shaped designs, blue-green deploys, and model-serving infrastructure — twenty years of web platforms underneath.
You get — infrastructure an auditor and an agent can both trust.
Explore cloud & MLOps →Kalshi API pipelines and MCP servers, arbitrage detection, and calibrated-probability tooling — where models meet money and get graded on it.
You get — probabilities with a P&L attached.
Explore quant tooling →The agent loop
Every agent I ship runs the same loop, and every step of it is measured. Agents, with adult supervision.
Signals in: your systems exposed as MCP tools, plus events, queues, and documents. The agent sees exactly what you let it see — scoped, logged, revocable.
Models plus evals: the model proposes, the eval suite grades. Model selection is a measured decision, not a brand preference.
Side-effects behind human gates: drafts, diffs, and proposals by default — writes only where you approved them, with an audit trail either way.
Memory plus monitoring: what worked lands in shared memory, what broke lands on the dashboards. The loop tightens every run.
Dogfood
The agentic stack I sell is the one I run. My multi-project operation is an agent fleet — twenty-plus Claude agent sessions coordinated like a small team.
This site, its deploys, and the tooling behind it are run by that fleet. Dogfooding is the eval.
See the live practice →Engagement models
Every problem is different, but engagements come in three shapes — pick the one that fits, or start with a conversation and we’ll find it together.
Advisory — audits, eval reviews, second opinions
Build — agent pilots, MCP servers, scoped systems
Retainer — operate the fleet, watch the dashboards
“An agent without evals is a liability with an API key.”
Ionel Roiban · working principle
Tell me what you want an agent to do. First conversation is free.
Book a consult