Project library

Full project depth, proof surfaces, and recruiter-readable outcomes.

The homepage now stays brief by design. This page carries the full project library, translation layer, and artifact vault so every major project can be treated seriously without overcrowding the landing page.

Browse projects Open web CV Contact Michael

Major projects

Equal-weight case studies spanning BI infrastructure, AI orchestration, predictive analytics, NLP, regression, and database design.

Proof policy

Public content stays derived and sanitized. Raw resumes, raw decks, and internal source material remain local-only inside the intake system.

Project library

Equal-weight project depth, without homepage bloat.

This is the canonical project surface for the portfolio. Every major project gets the same level of seriousness: problem, method, result, public-safe proof path, and recruiter-readable outcome.

Power BI + stakeholder adoption

Command Center BI Infrastructure

Live

sanitized

High confidence

Built scalable reporting systems that turned fragmented sales data into decision-ready operating visibility.

Headline outcome

Reporting cadence scaled beyond manual capacity

Power BIDAXPower QueryVBADatabricksStakeholder Discovery

Impact

20+ hours per week removed from manual reporting and follow-up effort

Proof path

• Sanitized dashboard walkthrough
• Automation process note
• Reporting template or scorecard handoff

Problem

Stakeholders needed clean opportunity visibility, recurring executive reporting, and adoption tracking inside a growing internal analytics hub.

Method

Translated stakeholder requests into Power Query transformations, DAX KPI layers, PBIX conversion and adoption models, and recurring reporting workflows backed by QA and documentation.

Result

Created a more scalable reporting backbone for sales enablement, self-serve decision support, and recurring executive trend reviews.

See dashboard Download template

CLI orchestration + durable context

Gemini/Codex Workflow Automation

Live

public

High confidence

Built a file-driven AI orchestration system that keeps Gemini CLI and Codex CLI aligned through durable context, reconciliation, and validation gates.

Headline outcome

Multi-agent AI work stopped depending on chat memory

ShellPythonGemini CLICodex CLIMCPn8n

Impact

100 automation scripts, 34 operating docs, and 58 research receipts in a working cross-model CLI workflow ecosystem

Proof path

• Public docs repository
• Architecture and runbook corpus
• Read-only local repo evidence

Problem

Long-running AI coding workflows break when context lives only in chat history and when handoffs across models or sessions are not durable.

Method

Designed a constitution-first repository around declarative intent, a reconciliation loop, blackboard coordination, Gemini/Codex bridge scripts, MCP and n8n automation lanes, and deterministic close-out gates.

Result

Created a working orchestration environment that treats AI collaboration like an operational system instead of a one-off prompt chain.

Open docs repo

Adidas IT · Gradient Boosting

Ticket Reassignment Prediction

Completed

sanitized

High confidence

Modeled IT ticket reassignment behavior to reduce escalation friction, rerouting cost, and downtime risk.

Headline outcome

Reassigned tickets averaged roughly a week longer to resolve

Pythonscikit-learnFeature EngineeringModel Evaluation

Impact

76% accuracy, 86% recall, 73% F1, and roughly $280K in modeled annual labor savings

Proof path

• Final presentation deck
• Adidas service poster
• Methodology brief

Problem

IT support workflows were bleeding time through preventable reassignments and misrouted work.

Method

Built a Gradient Boosting workflow around ticket urgency, service, category, and geography variables, then evaluated the model with accuracy, recall, precision, and F1.

Result

Produced a predictive decision aid that could be integrated into ticket submission to flag likely reassignments earlier.

View methodology

Regression + cross-validation

Spotify Popularity Prediction

Completed

public

Medium confidence

Used audio-feature data to model song popularity and translate statistical results into product and marketing recommendations.

Headline outcome

Turned audio features into business-readable popularity signals

PythonRegressionCross ValidationFeature AnalysisEDA

Impact

Statistically significant regression work with feature-level interpretation instead of inflated black-box claims

Proof path

• Phase 3 report
• Screen-recorded walkthrough
• Project proposal sequence

Problem

Needed to understand which measurable audio features aligned most with song popularity rather than relying on intuition alone.

Method

Applied multiple linear regression, correlation analysis, outlier handling, and cross-validation-oriented model evaluation to a Spotify feature dataset.

Result

Produced an interpretable modeling case study that surfaced which features mattered most and how that insight could shape promotion strategy.

View methodology

TF-IDF + logistic regression

Yelp Review Rating / Sentiment Modeling

Completed

public

Medium confidence

Built a text-mining workflow to classify Yelp review sentiment and surface operational signals from customer language.

Headline outcome

Customer review text became a usable service-improvement signal

PythonTF-IDFLogistic RegressionVADERFLAIR

Impact

High-accuracy sentiment classification paired with operational feedback signals a manager could act on

Proof path

• Final project report
• Final presentation deck
• Recorded walkthrough

Problem

Needed a structured way to turn large volumes of review text into actionable insight about customer sentiment and service issues.

Method

Applied text preprocessing, TF-IDF vectorization, VADER and FLAIR sentiment labeling, and logistic regression classification with standard evaluation metrics.

Result

Generated a model and business readout that highlighted where customer experience was strong and where wait time or staff issues were driving negative reviews.

Watch demo View methodology

Multivariable regression

TJIX Net Sales Drivers

Completed

public

High confidence

Linked advertising, e-commerce growth, and market trends to a business-readable net-sales growth story for TJX.

Headline outcome

Advertising and e-commerce were tied directly to net-sales upside

RegressionCorrelation AnalysisExcelDecision TreesScenario Modeling

Impact

Estimated ~$12.7M in net-sales lift per +$1M of advertising spend in the final model

Proof path

• Final report
• Supporting workbook
• Scenario summary

Problem

Needed to explain why TJX e-commerce penetration lagged peers and what levers could most credibly increase total net sales.

Method

Used regression, correlation analysis, scenario modeling, and competitor comparison to relate advertising and e-commerce growth to net-sales outcomes.

Result

Produced a business-facing argument for deeper e-commerce investment and more deliberate advertising support.

View methodology Download template

Access + SQL queries

Relational Database Design

Completed

public

High confidence

Designed a relational database structure to replace spreadsheet-driven project and staffing tracking for a growing IT support business.

Headline outcome

Operations data became structured, relational, and report-ready

Microsoft AccessSQLERD DesignNormalizationMetadata Design

Impact

Replaced spreadsheet thinking with a relational model built for queryability, consistency, and future growth

Proof path

• Final report
• Presentation deck
• ERD and metadata narrative

Problem

A growing IT support firm had outgrown shared spreadsheets, making staffing, project status, and customer support visibility hard to manage cleanly.

Method

Designed normalized entities, bridge tables, business rules, metadata, and query patterns for projects, employees, clients, assets, tickets, and services.

Result

Produced a database design built for cleaner reporting, resource allocation visibility, and operational scalability.

Download template View methodology

Impact lab

Business leverage deserves its own space, not a cramped homepage corner.

This is where the quantified story lives: modeled savings, automation compression, and recruiter-readable signal around what the work can do for a team when it moves from manual effort into repeatable systems.

Impact Analysis Dashboard

Recruiter-friendly proof of scale, business value, and technical range.

live signal

IT Routing Efficiency

Estimated annual savings

$280,000

Python, Gradient Boosting

Manual Reporting Automation

Value of reclaimed analyst time

$52,000

VBA, Power Query, DAX

Sales Driver Identification

Revenue signal surfaced

$12,700,000

Regression, stakeholder analysis

The ROI of Automation

Based on my work at Avnet (converting a 5-hour manual process to a 30-minute script), calculate how much I could save your team.

Manual Reporting (Hours/Week)10 hrs

Average Team Hourly Rate ($)$50/hr

Time Reclaimed (Yearly)

442 hrs

Estimated Cost Savings (Yearly)

$22,100

Translation layer

Raw business signal scanned into recruiter-ready proof.

This strip turns the actual shape of the work into something a recruiter can process fast: messy asks, KPI logic, and workflow notes crossing a scanner line and resolving into proof assets.

Raw signal

Scroll to scan

Proof asset

Power BI / KPI translation

Executive visibility surface

Command Center dashboard walkthrough

Fragmented opportunity reporting becomes a recruiter-ready walkthrough of KPI logic, adoption flow, and operating visibility.

See dashboard

Raw stakeholder askSCAN-2026-PROOF-1001

// PORTFOLIO_SIGNAL: SCAN-2026-PROOF-1001 // // STAKEH
OLDER_ASK: show pipeline clarity by region, owner, and
 segment // DEFINE KPI.win_rate = DIVIDE([wins],[oppor
tunities]) // GROUP BY fiscal_week, account_owner, mot
ion // REQUIRED_OUTPUT = executive trend view + self-s
erve drill path // OUTPUT.surface = Executive visibili
ty surface // OUTPUT.story = Command Center dashboard 
walkthrough // // PORTFOLIO_SIGNAL: SCAN-2026-PROOF-10
01 // // STAKEHOLDER_ASK: show pipeline clarity by reg
ion, owner, and segment // DEFINE KPI.win_rate = DIVID
E([wins],[opportunities]) // GROUP BY fiscal_week, acc
ount_owner, motion // REQUIRED_OUTPUT = executive tren
d view + self-serve drill path // OUTPUT.surface = Exe
cutive visibility surface // OUTPUT.story = Command Ce
nter dashboard walkthrough // // PORTFOLIO_SIGNAL: SCA
N-2026-PROOF-1001 // // STAKEHOLDER_ASK: show pipeline
 clarity by region, owner, and segment // DEFINE KPI.w
in_rate = DIVIDE([wins],[opportunities]) // GROUP BY f

Durable context / AI orchestration

Public systems proof

Workflow docs repository

Bridge scripts, blackboard coordination, and reconciliation logic resolve into a public-safe documentation layer that shows the automation system is real.

Open docs repo

Agent orchestration contractSCAN-2026-PROOF-1002

// PORTFOLIO_SIGNAL: SCAN-2026-PROOF-1002 // DECLARE d
esired_state = INTENT.md // LEASE blackboard.owner = a
tomic_file_lock // ROUTE bridge = gemini_cli <-> codex
_cli // CLOSEOUT = sync + check + archive + push // OU
TPUT.surface = Public systems proof // OUTPUT.story = 
Workflow docs repository // // PORTFOLIO_SIGNAL: SCAN-
2026-PROOF-1002 // DECLARE desired_state = INTENT.md /
/ LEASE blackboard.owner = atomic_file_lock // ROUTE b
ridge = gemini_cli <-> codex_cli // CLOSEOUT = sync + 
check + archive + push // OUTPUT.surface = Public syst
ems proof // OUTPUT.story = Workflow docs repository /
/ // PORTFOLIO_SIGNAL: SCAN-2026-PROOF-1002 // DECLARE
 desired_state = INTENT.md // LEASE blackboard.owner =
 atomic_file_lock // ROUTE bridge = gemini_cli <-> cod
ex_cli // CLOSEOUT = sync + check + archive + push // 
OUTPUT.surface = Public systems proof // OUTPUT.story 
= Workflow docs repository // // PORTFOLIO_SIGNAL: SCA
N-2026-PROOF-1002 // DECLARE desired_state = INTENT.md

Scorecard / repeatable ops tool

Download-ready artifact

Reporting template handoff

Loose spreadsheet logic turns into a polished template that an operator or manager could actually reuse without needing the backstory.

Download template

Operator handoff formatSCAN-2026-PROOF-1003

// PORTFOLIO_SIGNAL: SCAN-2026-PROOF-1003 // SOURCE = 
scorecard_columns, owner_flags, labor_notes // STANDAR
DIZE header_naming, status_bands, date_logic // LOCK f
ormula_cells = true // EXPORT handoff = public_safe_te
mplate // OUTPUT.surface = Download-ready artifact // 
OUTPUT.story = Reporting template handoff // // PORTFO
LIO_SIGNAL: SCAN-2026-PROOF-1003 // SOURCE = scorecard
_columns, owner_flags, labor_notes // STANDARDIZE head
er_naming, status_bands, date_logic // LOCK formula_ce
lls = true // EXPORT handoff = public_safe_template //
 OUTPUT.surface = Download-ready artifact // OUTPUT.st
ory = Reporting template handoff // // PORTFOLIO_SIGNA
L: SCAN-2026-PROOF-1003 // SOURCE = scorecard_columns,
 owner_flags, labor_notes // STANDARDIZE header_naming
, status_bands, date_logic // LOCK formula_cells = tru
e // EXPORT handoff = public_safe_template // OUTPUT.s
urface = Download-ready artifact // OUTPUT.story = Rep
orting template handoff // // PORTFOLIO_SIGNAL: SCAN-2

Analytical rigor for recruiters

Business-readable brief

Methodology brief

Model notes, QA choices, and business framing resolve into a short proof brief that explains what was built and why it mattered.

View methodology

Analysis notesSCAN-2026-PROOF-1004

// PORTFOLIO_SIGNAL: SCAN-2026-PROOF-1004 // MODEL = g
radient_boosting_classifier // METRICS = accuracy, rec
all, f1_score // QA = validation_split + stakeholder n
arrative alignment // DELIVERABLE = one_to_two_page_me
thodology_brief // OUTPUT.surface = Business-readable 
brief // OUTPUT.story = Methodology brief // // PORTFO
LIO_SIGNAL: SCAN-2026-PROOF-1004 // MODEL = gradient_b
oosting_classifier // METRICS = accuracy, recall, f1_s
core // QA = validation_split + stakeholder narrative 
alignment // DELIVERABLE = one_to_two_page_methodology
_brief // OUTPUT.surface = Business-readable brief // 
OUTPUT.story = Methodology brief // // PORTFOLIO_SIGNA
L: SCAN-2026-PROOF-1004 // MODEL = gradient_boosting_c
lassifier // METRICS = accuracy, recall, f1_score // Q
A = validation_split + stakeholder narrative alignment
 // DELIVERABLE = one_to_two_page_methodology_brief //
 OUTPUT.surface = Business-readable brief // OUTPUT.st
ory = Methodology brief // // PORTFOLIO_SIGNAL: SCAN-2

Stakeholder asks, KPI definitions, SQL, DAX, and workflow notes feed the left side.

The center scan line visualizes Michael’s strongest skill: translation under ambiguity.

The right side resolves into recruiter-speed proof assets already wired into the artifact vault.

Artifact vault

Proof surfaces, downloads, and recruiter-safe artifacts.

This is where public-safe screenshots, short briefs, downloadable templates, and demo media will land once each asset is cleared for sharing.

Sanitized asset slot

dashboard screenshots or short walkthrough video

dashboard

Command Center dashboard walkthrough

Projects · Translation layer · Artifact vault · Assistant

Planned public-safe dashboard surface for KPI tracking, adoption visibility, and executive reporting flow from the Command Center work.

Best fit: cropped Power BI screenshots or a short sanitized walkthrough from the Command Center reporting environment.

See dashboardpublic-safe asset planned

Download-ready slot

downloadable template, scorecard, or PDF export

template

Excel or reporting template

Artifact vault · Contact · Assistant

Planned downloadable scorecard, spreadsheet, or operating template that proves practical systems thinking rather than just presentation polish.

Best fit: a sanitized scorecard, checklist, or reporting template that a manager could actually reuse.

Download templatepublic-safe asset planned

Video slot

short video or annotated walkthrough

video

Automation demo

Projects · Translation layer · Artifact vault · Assistant

Planned short walkthrough of an automation flow, notebook, or reporting pipeline that turns recurring manual work into a repeatable system.

Best fit: a 30 to 90 second clip showing workflow compression, QA steps, and the final business-facing output.

Watch demopublic-safe asset planned

Methodology slot

PDF brief or web case-study page

pdf

Case-study methodology brief

Projects · Artifact vault · Assistant

Planned concise methodology brief that explains business problem, analytical method, QA thinking, and business outcome without exposing sensitive internal detail.

Best fit: a 1 to 2 page PDF or web case-study page for modeling, BI design, or workflow methodology.

View methodologypublic-safe asset planned

Public repo

public documentation repository

repo

Gemini/Codex workflow docs repository

Projects · Artifact vault · Assistant

Public documentation layer for the larger Gemini/Codex workflow automation system, including architecture notes, runbooks, and readiness receipts.

Public-safe companion repo for a much larger local automation workspace and CLI orchestration system.

Open docs repo