Work

Ideas into working systems.

AI workflows, semantic layers, metric governance, and data platforms. Explore the problem, approach, and outcome.

Professional workPersonal builds

Professional work

Latest professional project

Reporting Agent

Problem

People needed a practical way to explore business metrics, build dashboards, and produce data-backed artifacts from fully governed, clearly defined metrics.

Outcome

Enabled people to ask questions, build their own dashboards, and generate artifacts from a shared foundation of governed metrics, defined grains and segments, and continuously tested semantic models.

01 / Agree

Governance committee

Define metrics together.

02 / Model

Semantic layer

Explicit grains and minimum segmentation.

03 / Guide

Assistant plugin

Query data, conduct analytics, style dashboards.

04 / Validate

Continuous testing

Check implementations against definitions.

Shared definitions connect questions, dashboards, and data-backed artifacts.
Approach & decisions
  • I created a data governance committee to define business metrics and establish shared agreement on their meaning.
  • We implemented those metrics in the semantic layer with explicit grains—the level of detail each metric represents—and a defined minimum level of segmentation. Metric definitions, grains, and segments were fully documented and governed.
  • I designed a plugin for Claude combining reusable skills and a custom Model Context Protocol (MCP) interface to connect the assistant to the semantic layer and supporting tools.
  • The plugin guided how to query data, conduct analytics, and style dashboards, giving people a consistent workflow for conversational analytics, self-service dashboards, and artifacts generated directly from the data.
  • We established continuous testing on the semantic layer to keep its metric implementations aligned with the governed definitions.

Data architecture

Enterprise semantic layer for governed AI and analytics consumption

Problem

Analytics and AI consumption needed to scale from trusted metric definitions instead of duplicated logic, disconnected dashboards, or unsafe direct access to business data.

Outcome

Established a stronger foundation for consistent metrics, governed self-service, and AI-driven data consumption from approved enterprise definitions.

One definition, multiple consumersModeled data feeds governed business definitions in a semantic layer. Dashboards consume the semantic layer; AI agents and applications access metrics through a shared interface.Modeled dataBusiness definitionsSemantic layerDashboardsAI agentsShared interfaceAI applicationsShared interfaceReusable foundationsMetrics · Ownership · Context
Conceptual view of the semantic-layer case study.
Approach & decisions
  • Architected and delivered an enterprise semantic layer as a governed source of truth for business metrics.
  • Exposed trusted metrics through a governed interface for standardized consumption by AI agents, LLM-powered applications, conversational analytics, and self-service dashboards.
  • Connected governance practices to how teams define, discover, reuse, and safely consume business logic without disclosing confidential internal architecture or company data.

Analytics modernization

Analytics modernization and ELT acceleration

Problem

Data delivery was too slow and inconsistent for the needs of a modern analytics function.

Outcome

Reduced data modeling and delivery time by more than 80% within the first few months.

  • ELT
  • Modeling standards
  • Analytics engineering
  • Delivery acceleration
Approach & decisions
  • Implemented a modern ELT architecture.
  • Created modeling standards and framework documentation.
  • Built a roadmap that aligned engineering execution with analytics delivery priorities.

Revenue systems

Revenue systems and product-led growth architecture

Problem

Self-service customer journeys needed stronger systems, data flows, and account intelligence to surface growth opportunities.

Outcome

Unlocked more than $15M in ARR opportunities and supported operating scale during company growth.

  • Revenue systems
  • Reverse ELT
  • Business applications
  • Product-led growth
Approach & decisions
  • Architected self-serve GTM systems across product usage and account intelligence.
  • Implemented modern warehouse, ELT, and reverse-ELT patterns.
  • Managed the business systems portfolio and cross-functional technical delivery.

Personal project / Data, semantics & AI

CaptGabe Fitness

Built for my own training. A framework I want to grow and scale.

Actual CaptGabe Fitness dashboard showing a planned lower-body workout and nutrition targets
Actual dashboard · September 29, 2026 · Planned session and daily targets; no food logged that day. Select to enlarge.

The builder instinct

I wanted to create an app for myself, then build the framework to support its growth. The detailed expansion plan is still to come.

The feedback loop

From entries to a personal assistant.

Structured workout records feed data models. Metric definitions give ChatGPT consistent meaning when discussing progress and adjustments.

“How has my incline press progressed?”

“Where has performance stalled?”

“What should we adjust next session?”

Why the semantic layer matters

A shared definition of each metric makes comparisons consistent. The assistant can discuss training history in the context of exercises, sets, load, and planned targets.

I choose the adjustment, complete the next workout, and bring those results back into the same feedback loop.

01 / Capture

Training, nutrition & measurements

Workout entries, sets, reps, load, food logs, and body measurements.

02 / Store & model

Fitness data models

Workouts → exercises → sets, alongside food entries, measurements, programs, and planned targets.

03 / Define meaning

Semantic & metric layer

Reusable views for latest exercise performance, daily nutrition actuals, and progress against the plan.

Dashboard

See the progress

The authenticated app reads data and metric views through its dashboard API.

Assistant workflow

Ask ChatGPT

Explore fitness metrics, discuss patterns, and use training history to inform the next workout.

Close the loop ↺

Review the recommendation → choose an adjustment → train → record the next session.

Data models, metric views, and dashboard access are reflected in the app source. The dashed assistant branch represents the ChatGPT workflow; its connection is managed outside this app repository.

Personal build

This website

AI-assisted editing, version control, and automated publishing shorten the path from idea to a finished page.

Explore the build