Technology built around real-world problems.
A selection of representative demonstrations illustrating how I approach artificial intelligence, construction data, enterprise application development, and cloud architecture.
From construction data to intelligent project systems.
My work sits at the intersection of construction operations, project controls, software engineering, data, and artificial intelligence. The demonstrations below are intentionally representative rather than production screenshots. They illustrate the technology, architecture, and workflows behind systems I have designed and developed without exposing confidential organizational information.
AI Project Intelligence
Turning complex construction project data into information that project teams can understand, search, and act on.
Construction projects generate large amounts of information across schedules, project updates, milestones, risks, financial data, contacts, and other project-control systems. The challenge is turning that information into useful intelligence without requiring users to search through multiple systems manually.
- An ASP.NET Core project intelligence application
- AI-assisted project analysis using Google GenAI
- Semantic search using vector embeddings
- Project-specific conversational AI
- Structured construction data integrated with AI
- Streaming AI responses through the web application
The project is experiencing a permit-related schedule risk. Recent project activity indicates a potential downstream impact to the construction start date.
Semantic Construction Search
Helping project teams find relevant construction information based on meaning and context—not just exact keyword matches.
Construction organizations accumulate large amounts of project information across updates, schedules, specifications, risks, correspondence, and project-control records. Traditional keyword searches can miss information when the wording used by the user differs from the wording stored in the underlying data.
- Semantic search using vector embeddings
- Construction-specific document indexing
- Similarity-based retrieval of relevant content
- Search results ranked by semantic relevance
- AI-ready retrieval architecture for project data
- Integration of semantic retrieval with enterprise application workflows
Long-lead mechanical equipment remains an important factor in the planned construction sequence and equipment delivery schedule.
Installation activities are dependent on equipment availability and coordinated delivery of mechanical systems.
Procurement timing should be monitored because delays in equipment availability may affect downstream construction work.
Coordination activities include review of mechanical systems, equipment requirements, and installation sequencing.
Construction Data Integration
Turning fragmented construction systems into a connected, reliable data foundation for reporting, analytics, and AI.
Construction data rarely starts in one place.
Project information is often distributed across scheduling systems, project management platforms, financial systems, document repositories, and operational databases.
The challenge is not simply collecting the data. It is creating a dependable structure that allows information from different systems to be combined, transformed, validated, and used consistently.
A construction data integration foundation.
I have designed and implemented data pipelines that move construction information from source systems into structured SQL Server environments where it can support reporting, project controls, analytics, application workflows, and AI capabilities.
The architecture separates source-system ingestion, transformation, business logic, and presentation so downstream applications do not have to understand the complexity of every originating system.
AI is only as useful as the data behind it.
Reliable project intelligence requires more than an AI model. It requires trustworthy project information, consistent business rules, historical context, and data structures that applications can query efficiently.
This data engineering layer provides the foundation that allows higher-level AI capabilities to operate against meaningful construction information.
Construction information begins across multiple systems and operational sources. Schedules, project updates, financial information, documents, and other records provide the raw project data.
Enterprise AI Architecture
Connecting enterprise applications, construction data, semantic intelligence, and generative AI into a cohesive technology architecture.
AI cannot exist in isolation.
Enterprise AI applications must operate within the larger technology environment that already supports the organization.
That means connecting user interfaces, application logic, construction data, search capabilities, AI services, databases, security, and cloud infrastructure into a system that can evolve over time.
An architecture connecting data to intelligence.
I have worked across the application, data, cloud, and AI layers required to turn enterprise information into practical project intelligence.
The architecture combines ASP.NET Core applications, SQL Server data platforms, semantic search, Google Cloud services, and generative AI into connected workflows.
Keep intelligence close to the business context.
AI becomes significantly more useful when it can understand the organization's own data, terminology, workflows, and business rules.
The architecture therefore places AI inside the application and data ecosystem rather than treating the model as a standalone destination.
The architecture begins with the people and applications consuming project information. Dashboards, project tools, and AI assistants provide the user-facing experience.
Construction Management Platform
Building enterprise applications that connect project controls, schedules, risks, milestones, financial information, and operational workflows into a unified project environment.
Construction teams need more than disconnected tools.
Large construction programs generate enormous amounts of information across project controls, schedules, milestones, risks, financial commitments, documents, approvals, and operational updates.
The challenge is creating an application environment where that information can be brought together and presented in a way that helps project teams understand what is happening and what requires attention.
Enterprise construction management applications.
I have designed and developed web applications that bring construction information together into structured workflows for project managers, project controls teams, administrators, and leadership.
These applications combine data grids, dashboards, workflow interfaces, project controls, business rules, role-based access, reporting, and integrations with enterprise data sources.