CPA · Agentic AI & Automation · Enterprise Finance Transformation

Finance should own its own intelligence.

CPA with over 15 years across finance, SAP, and enterprise systems. Multiple full-cycle S/4HANA implementations in aviation, mining, pharma, and public sector. Now building multi-agent AI systems that solve real finance problems — same ownership mindset, new layer.

5Assets Built
89%Cost Reduction
$0.00Recon Error
3-TierConfidence Scoring

The through-line

Started as a CPA — financial analyst, external auditor, a decade of practicing finance. That background shapes everything I do in ERP and AI.

Spent over 15 years in finance and transformation: multiple full-cycle S/4HANA implementations across regulated industries. Went deep on Controlling, Project System, financial close — and took ownership of the data migration layer (LTMC, Migration Cockpit, LSMW, LTMOM). A senior functional consultant should own everything in their domain.

Now applying that same mindset to agentic AI. Building autonomous agents, wiring them to ERP systems, owning the intelligence layer the way I owned the data layer.

The Progression
01
Foundation
Practicing CPA
Financial analyst · External audit · CPA designation
02
ERP & Finance
SAP FICO / RTR / PS Consultant
Multiple S/4HANA implementations · 7 SAP certifications
03
Data ownership
Functional-Led Data Migration
LTMC · Migration Cockpit · LSMW · LTMOM custom templates · BAPIs
04
Current
Business Architecture Manager
Enterprise SAP delivery · Regulated industries
05
Building now
Agentic AI Architect
Multi-agent systems · ERP integration · Domain-owned intelligence

Design philosophy

One rule: LLMs reason, tools compute. The AI classifies and routes. Deterministic tools do the math and generate files. Governance is built in from the start — confidence scoring, escalation thresholds, structured validation at every handoff.
Cost discipline

Agents pass structural summaries, not raw data. Most expensive run across all five assets: $0.46 for a four-report financial statement bundle.

Responsible AI

Confidence-based posting thresholds. Human-in-the-loop escalation. Structured audit trails. The agent augments judgment, doesn't replace it.

Backend-agnostic

The intelligence layer belongs to finance, not the ERP vendor. Agent patterns transfer directly across platforms.

What I built

Five agentic AI systems. Each solves a real enterprise finance problem — designed, built, tested, and validated independently at near-zero cost.

Built independently · Near-zero cost · Production-grade accuracy
ASSET 01
GL Aggregation Agent

Profitability analysis required recurring aggregation of high-volume GL data — grouped by multiple keys, reconciled to the penny, with zero tolerance for error.

$0.03Cost per run
41sExecution time
89%Cost optimized
↗ View details
ASSET 02
Master Data Ticket Processor

SAP master data creation from service tickets was fully manual — read, extract, validate, build the upload, update the status. Every record. Every time.

$0.13Per record (bulk)
E2EJira integrated
AutoReprocess loop
↗ View details
ASSET 03
Invoice → Journal Entry Agent

AP invoice processing — matching line items to GL accounts and producing balanced journal entries — relied on manual accounting judgment that didn't scale.

10/10Accuracy
~$0.30Cost per run
3-tierConfidence scoring
↗ View details
ASSET 04
SAP Operations Hub

Multiple pipelines for different SAP operations meant users had to know which tool to use. The goal: one entry point that understands intent and routes intelligently.

1Entry point
7Agents orchestrated
SmartIntent routing
↗ View details
ASSET 05
End-to-End Accounting Agent

The full accounting cycle — journal entries, AP and AR invoices, Business Partner creation, financial reporting — required multiple manual steps across the ERP. The goal was a single orchestrated agent handling the complete lifecycle.

8Agents
14Tools
E2EGL → Reports
~$0.22Per report
↗ View details

The foundation

The AI work is credible because of what's underneath it.

Layer 01 · Finance
The CPA foundation. A decade of practicing finance before SAP.
Chartered Professional Accountant
Financial Analysis
External Audit
Financial Close & Reporting
Controlling & Profitability Analysis
Bilingual · English / French
Layer 02 · SAP + Data
Functional depth plus the data layer — owned end-to-end.
SAP FICO (FI + CO)
Record-to-Report (RTR)
Project System (PS)
FICA / FSCD
Multiple Full-Cycle S/4HANA Implementations
LTMC · Migration Cockpit
LSMW (non-standard scenarios)
LTMOM Custom Templates
BAPI-Based Custom Loading
Layer 03 · AI Architecture
The intelligence layer — the next frontier of the senior functional role.
Multi-Agent Pipeline Design
Hub-and-Spoke Orchestration
Model Context Protocol (MCP)
RAG (Retrieval-Augmented Generation)
Confidence Scoring & Routing
Token Optimization
Responsible AI / Governance
Cross-Platform Agent Design
ERP & API Integration
Delivery & Leadership
Business Architecture Manager · Enterprise SAP
SAP Joule for Consultants (J4C) Lead · Major airline engagement
Agentic AI Bootcamp · Nominated · Chicago 2026
Team Lead · Direct reports
Interviewer · Graduate & experienced hires
// 5 assets built independently  ·  // $0.03 per run  ·  // 89% cost reduction  ·  // 10/10 accuracy  ·  // $0.00 reconciliation error  ·  // 3-tier confidence scoring  ·  // CPA + SAP + AI  ·  // Near-zero dev cost  ·  // 5 assets built independently  ·  // $0.03 per run  ·  // 89% cost reduction  ·  // 10/10 accuracy  ·  // $0.00 reconciliation error  ·  // 3-tier confidence scoring  ·  // CPA + SAP + AI  ·  // Near-zero dev cost  · 

Let's talk.

Open to conversations about AI-enabled finance transformation.