ATLAS Spec-to-Span
ATLAS Spec-to-Span
ATLAS Spec-to-Span
An ontology-driven configurator for complex engineering systems
An ontology-driven configurator for complex engineering systems
An ontology-driven configurator for complex engineering systems
As a sole product engineer and deployment strategist, I built end-to-end a 0-to-1 quote-to-drawing platform for a 3D-printed structural composites company. An operations system that incorporates engineer quoting automation, data management and multi-user workspace.
As a sole product engineer and deployment strategist, I built end-to-end a 0-to-1 quote-to-drawing platform for a 3D-printed structural composites company. An operations system that incorporates engineer quoting automation, data management and multi-user workspace.
As a sole product engineer and deployment strategist, I built end-to-end a 0-to-1 quote-to-drawing platform for a 3D-printed structural composites company. An operations system that incorporates engineer quoting automation, data management and multi-user workspace.
ATLAS Spec-to-Span turns a complex catalog and quoting workflow into a structured, visual experience for sales teams and engineering partners.
About ATLAS: MIT News
Live at: sales.atlsinc.com
ATLAS Spec-to-Span turns a complex catalog and quoting workflow into a structured, visual experience for sales teams and engineering partners.
About ATLAS: MIT News
Live at: sales.atlsinc.com
ATLAS Spec-to-Span turns a complex catalog and quoting workflow into a structured, visual experience for sales teams and engineering partners.
About ATLAS: MIT News
Live at: sales.atlsinc.com
ROLE
ROLE
ROLE
Deployment Strategist, Product Engineer
Deployment Strategist, Product Engineer
Deployment Strategist, Product Engineer
SKILLS
SKILLS
SKILLS
Client workshops
System architecture
Data modeling
Full-stack development
Client workshops
System architecture
Data modeling
Full-stack development
Client workshops
System architecture
Data modeling
Full-stack development
TIMELINE
TIMELINE
TIMELINE
2026
2026
2026
TOOLS
TOOLS
TOOLS
FastAPI, Pydantic, React, TypeScript
Three.js, Rhino 3D, CAD, Figma
Claude API, Claude Code
FastAPI, Pydantic, React, TypeScript
Three.js, Rhino 3D, CAD, Figma
Claude API, Claude Code
FastAPI, Pydantic, React, TypeScript
Three.js, Rhino 3D, CAD, Figma
Claude API, Claude Code
TEAM
TEAM
TEAM
Mechanical engineer (domain data)
CEO (product direction)
Ops consultant (deployment)
Mechanical engineer (domain data)
CEO (product direction)
Ops consultant (deployment)
Mechanical engineer (domain data)
CEO (product direction)
Ops consultant (deployment)
01 Overview
01 Overview
01 Overview
ATLAS company’s ROI suffers from a time-consuming manual quoting process and scattered information management. I came in to design a configurator system that manages the company’s system data and generates complex engineering quotes.
ATLAS company’s ROI suffers from a time-consuming manual quoting process and scattered information management. I came in to design a configurator system that manages the company’s system data and generates complex engineering quotes.
ATLAS company’s ROI suffers from a time-consuming manual quoting process and scattered information management. I came in to design a configurator system that manages the company’s system data and generates complex engineering quotes.
Getting to know the client
Getting to know the client
Getting to know the client
An MIT-incubated startup spun off from the MIT Laboratory for Manufacturing and Productivity, 3D-prints building composites from recycled waste plastic.
As their projects grew, more stakeholders (the U.S. Army Corps of Engineers, Gensler, etc.) are involved, quoting and product management outran their file management, configuration, storage, and auditing.
An MIT-incubated startup spun off from the MIT Laboratory for Manufacturing and Productivity, 3D-prints building composites from recycled waste plastic.
As their projects grew, more stakeholders (the U.S. Army Corps of Engineers, Gensler, etc.) are involved, quoting and product management outran their file management, configuration, storage, and auditing.
An MIT-incubated startup spun off from the MIT Laboratory for Manufacturing and Productivity, 3D-prints building composites from recycled waste plastic.
As their projects grew, more stakeholders (the U.S. Army Corps of Engineers, Gensler, etc.) are involved, quoting and product management outran their file management, configuration, storage, and auditing.
Working sessions and pain points
Working sessions and pain points
Working sessions and pain points
Weekly sessions with mechanical engineering, R&D, operations, and leadership to map workflows and locate the pain points. The core issue was disorganized files and data logging: nothing moved between departments without manual effort.
Weekly sessions with mechanical engineering, R&D, operations, and leadership to map workflows and locate the pain points. The core issue was disorganized files and data logging: nothing moved between departments without manual effort.
Weekly sessions with mechanical engineering, R&D, operations, and leadership to map workflows and locate the pain points. The core issue was disorganized files and data logging: nothing moved between departments without manual effort.
Data pipeline
Data pipeline
Data pipeline
I streamlined the catalog, quoting logic, and sales workflow into reusable components, established naming standards for files, and created a comprehensive pipeline including a workbook, JSON catalog, edit logging sync, and tests.
I streamlined the catalog, quoting logic, and sales workflow into reusable components, established naming standards for files, and created a comprehensive pipeline including a workbook, JSON catalog, edit logging sync, and tests.
I streamlined the catalog, quoting logic, and sales workflow into reusable components, established naming standards for files, and created a comprehensive pipeline including a workbook, JSON catalog, edit logging sync, and tests.
Scroll Left
Scroll Left
02 Solution
02 Solution
02 Solution
The client's four products (bridge, floor, deck, boardwalk) are one system: a hanger, trusses in its slots, another hanger, repeated. I built a single resolver, and product types became JSON presets over it.
The client’s four products (bridge, floor, deck, boardwalk) are one system: a hanger, trusses in its slots, another hanger, repeated. I built a single resolver, and product types became JSON presets over it.
The client’s four products (bridge, floor, deck, boardwalk) are one system: a hanger, trusses in its slots, another hanger, repeated. I built a single resolver, and product types became JSON presets over it.
System architecture
System architecture
System architecture
A few rounds in, I realized the real need wasn't an AI platform that assembles two drawing sets. It was linking three things that had never been linked:
Data management, storage, and product configuration
Sales quotes and customer communication
R&D file intake and multi-team operations
A few rounds in, I realized the real need wasn’t an AI platform that assembles two drawing sets. It was linking three things that had never been linked:
Data management, storage, and product configuration
Sales quotes and customer communication
R&D file intake and multi-team operations
A few rounds in, I realized the real need wasn’t an AI platform that assembles two drawing sets. It was linking three things that had never been linked:
Data management, storage, and product configuration
Sales quotes and customer communication
R&D file intake and multi-team operations
Scroll Left
Scroll Left
Ontology-driven
Ontology-driven
Ontology-driven
I designed the underlying system of the platform as an ontology: objects, relationships that carry their own evidence, axioms and actions, each writing an immutable audit row.
The goal is for each change to be trackable and to support LLM chain-of-thought reasoning that provides reliable answers for the AI agent.
I designed the underlying system of the platform as an ontology: objects, relationships that carry their own evidence, axioms and actions, each writing an immutable audit row.
The goal is for each change to be trackable and to support LLM chain-of-thought reasoning that provides reliable answers for the AI agent.
I designed the underlying system of the platform as an ontology: objects, relationships that carry their own evidence, axioms and actions, each writing an immutable audit row.
The goal is for each change to be trackable and to support LLM chain-of-thought reasoning that provides reliable answers for the AI agent.
03 Design
03 Design
03 Design
The final system balances technical precision with a more legible visual language, helping teams move from parts to proposals with confidence.
The final system balances technical precision with a more legible visual language, helping teams move from parts to proposals with confidence.
The final system balances technical precision with a more legible visual language, helping teams move from parts to proposals with confidence.
Design ideation
Design ideation
Design ideation
I developed a visual system that makes complex engineering decisions legible without flattening the technical detail.
I developed a visual system that makes complex engineering decisions legible without flattening the technical detail.
I developed a visual system that makes complex engineering decisions legible without flattening the technical detail.
