AI Product · Solutions · Delivery · Orlando, FL

Agentic AI that solves the business problem.

Anyone can demo an agent. I build the ones that solve a real problem and survive production. Tested against real cases, governed for safety, and measured by the outcome: revenue, savings, risk reduced. That’s how 110+ of them ended up running in healthcare, finance, and government, behind a patent and an AWS-published architecture. I am the translator between the C-suite that wants ROI and the engineers who build it.

View as
data → understanding → action
$40M+
revenue influenced (career)
$500M+
identified client savings
110+
specialized agents
2.5M+
contracts processed (Doczy.ai)
442B+
tokens processed
99%+
production accuracy
451
research citations
9
h-index
AWS Architecture Blog Peer-reviewed · ASCE 451 citations · Scholar Patent · Doczy.ai (2025) PhD · ML / applied-AI · PMP · PMI-PBA

Built for regulated environments: model-risk governance, prompt-injection isolation, cite-or-refuse grounding, and confidence-scored human-in-the-loop on every production system. See the approach →

Selected case studies

Seven that show the range

Document intelligence, a company I founded and led, payer policy, procurement, governed clause review, fraud, and credit. Each one started as a business problem I translated into an agentic system. Click any to open the full breakdown.

See all projects by sector →
Beyond building

Beyond client delivery, I co-lead roughly $6.8M in internal AI investment programs for 2026, reinventing how the firm itself works with AI. I run this kind of multi-program slate year over year.

$3M
AI SaaS product build
$2.5M
config-engine program budget
$1.3M
network cost-analytics program
$6.8M
total 2026 investment programs
Work · by sector

42 projects, grouped by the problem they solve

Clients anonymized; public repos linked. Click Details for problem, approach, architecture, stack, output, impact, and the framework rationale. Filter by industry or technology to jump to relevant work.

Industry
Tech
Skills

From running the program to writing the code

I lead AI delivery at the executive level and still build the systems myself. Highlighted chips are the technologies I use as a primary stack across projects, drawn from the cross-project tech matrix.

core stack used across production systems    familiar working knowledge
01

Executive & Delivery Leadership

AI program leadership ($6.8M programs)10+ concurrent workstreamsvalue frameworkvalue-based pricingchange managementC-suite & stakeholder alignmentteam building (25-person team)mentoring (15+ engineers)delivery ownershiproadmappingvendor governancehiring & coaching
02

AI & Agentic Engineering

AWS BedrockLangGraphLangChainCrewAIAWS StrandsBedrock AgentCoreModel Context Protocol (MCP)Nova Actmulti-agent orchestrationRAGprompt engineeringtool-callinghuman-in-the-loop designevals & guardrailsreasoning & planningstructured outputs (JSON)agent memory
02b

Claude Skills · Agent Specialization

Claude Skills authoringmy-builder (investigate, write requirements and plans, approval gate, then build)my-investigatormy-testermy-observer (LangFuse-style tracing)my-roadmap (large features split with HITL)approval-gated workflowsspec-first development
03

ML & Data Science

XGBoostSHAP (explainability)Random ForestLightGBMscikit-learnGraph Neural Nets (PyG)Genetic AlgorithmsNeural NetworksAutoMLPCA / t-SNEnested cross-validationfeature engineeringReinforcement Learningforecasting & optimizationtime-seriesclustering
04

Cloud, Data & MLOps

Amazon TextractAmazon S3AWS LambdaAmazon ECSCognitoAPI GatewayDynamoDBCloudWatchSnowflakeDatabricks (delivery oversight)PostgreSQLQdrantRedisLangFuse (observability)DockerGeoPandasETL pipelines
05

Product & Full-Stack

Python 3.11FastAPIReact 18 / 19Next.jsTailwindWebSocketstRPCpython-docx / pptxDuckDB-WASMPlotly / FoliumTypeScriptREST / streaming APIsCognito auth
06

Governance, Safety & Compliance

model-risk managementbias / drift / adversarial testingexplainability for regulatorsprompt-injection isolationdeterministic guardrailsconfidence-scored HITLimmutable audit trailsHIPAA / HITRUSTBAAs & zero-training clausesPII tokenization
07

Domain Expertise

Healthcare payer operationsFinancial services: fraud, credit, pricingProcurement & spendSupply chainContract / CLM intelligenceClinical data (FHIR / HL7, Clinical NLP)Transportation & government
08

Research & Credentials

PhD, ML / applied-AI (UCF)451 citationsh-index 920+ peer-reviewed papersAWS Architecture BlogIEEE Access · MDPI · ASCE journalspatent (Doczy, 2025)PMPPMI-PBASAFeAWS Solutions Architect cert (2026)
The approach

The hard part of enterprise AI isn't the model. It's making it solve a real problem, in production, that people trust.

That gap is where most AI projects die, and closing it is what I do. I am the translator between the C-suite that wants ROI and the engineers who want to build, and I've closed that gap as a researcher, a founder, and now a delivery director: understand the business pain, design the architecture, build and evaluate the agents, govern them for safety, and tune them until they hold up. I still write the code and the reference architectures myself.

How I work

From a business problem to a production system

Five steps. Each one exists because skipping it is exactly where single-prompt demos fall apart.

01

Understand the problem

Sit with the operators. Find where the money, time, and risk actually are, and define the outcome and its metric before any model.

02

Design the architecture

Decompose into single-purpose agents, put deterministic code where guarantees matter, and choose the right pattern and framework per problem: LangGraph, CrewAI, Strands, AgentCore, or deterministic orchestration.

03

Build & evaluate

Write evals against real cases first, encode domain rules into the prompts, wire strict JSON tool contracts. Iterate on the eval set, not on vibes.

04

Govern for trust

Confidence-scored human-in-the-loop, explainability, prompt-injection isolation, and an immutable audit trail. Confidence ≠ correctness.

05

Optimize & operate

Tune cost, accuracy, and latency together with model routing and caching. Measure tokens and dollars per outcome, and watch it in production.

The trust pillar

Enterprise adoption of frontier models lives or dies on trust. Confidence ≠ correctness is the principle I build by.

  • Confidence-scored human-in-the-loop on every production pipeline
  • Explainability that satisfies regulators, not just engineers
  • Prompt-injection isolation and deterministic output guardrails
  • Incident response: rollback, disable, immutable audit trail
  • Model-risk management: bias, drift, adversarial testing before deploy
  • Vendor governance: BAAs, zero-training clauses, PII tokenization
Governed autonomy, measured

Autonomy is earned with evidence, not claimed.

85% validated auto-approvefrozen regression baselinesU-flags never auto-approve0 silent failures68 offline tests

My latest engine, a 7-agent contract clause assessor, ships 85% of its assessments with no human review because every release must reproduce two frozen baselines before it counts. The other 15% routes to a person by deterministic rule, not model mood. That is what governed autonomy means in practice.

The balancing act

Safety and performance are not a trade-off. I engineer for both.

Every production system has to clear the non-negotiables (safety, governance, grounding) and still hit its numbers (accuracy, cost, latency). Here is how I hold both at once.

Non-negotiables first

Grounding, guardrails, confidence-scored human-in-the-loop, and audit trails are entry criteria, not features. If a system can't clear them it doesn't ship, however good the metrics look.

Then optimize the triangle

Accuracy, cost, and latency trade against each other. I tune them together: right-size the model per step, route easy cases to cheaper models, cache aggressively, and measure tokens and dollars per outcome.

Framework & reasoning selection

I fit the pattern to the problem: LangGraph for stateful multi-step control, CrewAI for role-based crews, Strands and AgentCore for AWS-native deployment, deterministic orchestration where guarantees matter, and text-to-SQL or RAG by the shape of the data.

Prove it with evals

Real-case eval sets decide every change. Nothing ships on vibes, and regressions are caught before users ever see them.

What I bring to the table

Not a model-caller. A builder who ships, and owns the outcome.

Translator

I sit between the C-suite that wants ROI and the engineers who want to build. I turn business problems into agentic systems, and agents into revenue, savings, and risk reduced.

Builder

I write the code and the reference architectures myself. A U.S. patent, an AWS-published architecture, and 110+ agents running in production.

Founder & CEO

Brane: raised $625K, built and led a 25-person team, now building an AI grid-planning platform. I know exactly what 0→1 costs.

Program leader

I co-lead ~$6.8M in AI investment programs for 2026 on top of a multi-client delivery portfolio, with value frameworks and value-based pricing. I turn AI from a demo into a business line, year over year.

Researcher

PhD in ML / applied AI, 451 citations, h-index 9, published in ASCE and MDPI. I read the papers and I ship the systems.

About

Builder, translator, founder, program leader, researcher.

I'm an AI product and solutions leader who takes agentic systems from a blank page to production inside regulated enterprises, and I own the outcome end to end. I designed the architecture and led the build of a GenAI document-intelligence platform (Doczy.ai) that reached $15M+ in revenue, $330M+ in client savings, a 2025 patent, and a feature on the AWS Architecture Blog, processing 2.5M+ contracts at 99%+ accuracy, and I've shipped 40+ systems and 110+ specialized agents across six industries.

Consulting taught me the other half of the job: I am the translator. I sit between the C-suite that wants ROI and the engineering teams that want to build, turning business problems into agentic systems and agents into revenue, savings, and risk reduced, and I win the room from discovery and pre-sales through close with the executives and non-technical stakeholders who own the budget. And I don't just build, I co-lead multiple multi-million-dollar AI programs: in 2026, roughly $6.8M in internal AI investment programs: an AI SaaS product build ($3M), a healthcare configuration automation engine ($2.5M), and a network cost-analytics program ($1.3M), with value-and-prioritization frameworks, change management, and value-based pricing. I've run this kind of multi-program slate year over year.

Before consulting I founded a smart-mobility startup: raised $625K, built and led a ~25-person team, ran USDOT and SBIR collaborations. I earned a PhD applying machine learning to forecasting (20+ papers, 451 citations, h-index 9, published in IEEE Access, MDPI, and ASCE journals) and taught project management to engineering students at UCF.

My conviction: the hard part of enterprise AI isn't the model. It's understanding the real business pain point, designing the right solution architecture, and building in the governance that makes it trustworthy. I still write the code and the reference architectures myself: framing the problem, designing the optimal architecture, building and testing it with human-in-the-loop, and tuning cost, accuracy, and latency until it holds up in production.

At a glance

Role · Director, AI & Data Science
2026 programs · ~$6.8M in internal AI investment programs
2026 YTD · 57 AI initiatives across clients, product, and internal ops
PhD · Engineering, ML / applied-AI, UCF
Research · 451 citations · h-index 9 · 20+ papers
Patent · Doczy.ai (2025)
Certs · PMP · PMI-PBA · SAFe · AWS & CCA (2026)
Building AI organizations

Teams are systems too. I have built them from zero twice.

0 → 25
Built and led a 25-person cross-functional team as co-founder and CEO of Brane Mobility
~15
AI scientists and engineers I lead and mentor today, with leads owning workstreams under me
$6.8M
2026 internal AI investment programs I co-lead across three initiatives
Academy
Founded Modern AI Academy, teaching engineers and business users how agentic systems get built

I build teams the way I build systems: clear ownership, evals for everything, autonomy that is earned. Engineers I have mentored now run their own workstreams and teach the standards forward, which is the only leadership metric I fully trust.