Problem
Founders often start with broad ideas but no repeatable way to turn an industry choice into a realistic plan, staffing model, income assumptions, or startup sequence.
R&D case study
NAICS Startup Planning System
Planning system that turns broad startup ideas into structured, traceable business planning steps.
At a glance
Delivery stage
R&D
Current state
Prototype
My role
Sole architect and full-stack engineer
What was built
Built as an offline-first planning engine backed by the full NAICS hierarchy. The system combines rules-based role generation, income modeling, dependency-ordered startup procedures, and explainability views so users can inspect why each recommendation was produced.
Result
Working planning engine with rules-based role generation, income modeling, and explainability views across NAICS hierarchy
How the system was structured
This section shows the operational logic behind the build, not just the user-facing surface.
Key system pieces
Rules engine converts industry data into launch-plan structure.
Explainability layers make the output inspectable rather than magical.
Offline-first runtime keeps the system usable without external APIs.
Core constraint
Explainability: every generated recommendation must trace back to a rule, data source, or constraint, not a black-box model
Stack
Next.jsPrismaSQLiteZodRules EngineSnapshot Tests
Proof status
This page separates what is already visible from what is still being prepared, so the proof layer can grow without pretending unfinished artifacts already exist.
Proof surfaces
Real artifacts stay visible. Missing artifacts are labeled directly so this page stays honest and ready for stronger proof later.
System Walkthrough
Available nowThe current walkthrough is grounded in how the rules engine turns category data into traceable planning output.
- The planning flow shows how an industry choice becomes a generated operating plan.
- Explainability views make each recommendation inspectable rather than magical.
Architecture / Flow
Available nowThe planning engine diagram on this page shows how data, rules, and output generation are connected.
- NAICS hierarchy feeds the planning engine.
- Rules engine drives role generation, income modeling, and procedural ordering.
- Explainability layer exposes why the system made each recommendation.
Operational Surfaces
Available nowThe system has clear operator surfaces even though it is still at the prototype stage.
- Planning outputs can be inspected and exported.
- Rules trace gives users a way to verify recommendations.
- Offline-first runtime removes dependence on external APIs for core behavior.
Artifacts & Evidence
Available nowCurrent evidence is centered on rules, diagrams, and generated outputs.
- Planning engine diagram on this page.
- Rules trace supporting explainability claims.
- Generated plan artifacts available for later inclusion.
Related case studies
More work at a similar delivery stage.
Active Build
Proof surface in progress
Architecture / Flow
The current architecture direction is already clear even though the full artifact set is not published yet.
R&DActive BuildApplied AI & Automation Systems
WeatherForge
Weather-triggered signal and routing system in active development to turn storm activity into usable operational input for StormIQ.
My Role
Sole architect and engineer building the system foundation
Outcome
System boundaries are defined for signal ingestion, normalization, territory relevance, and downstream routing; implementation is in progress
PythonFastAPIGeospatial ProcessingEvent Routing
Read case studyActive Build
Proof surface in progress
Architecture / Flow
The architecture direction is already concrete: stateful orchestration, controlled branches, and explicit review seams.
R&DActive BuildApplied AI & Automation Systems
DGM
Workflow orchestration layer in active development for managing state, decision flow, and human review inside StormIQ.
My Role
Sole architect and engineer building the orchestration layer
Outcome
Execution model is defined for graph-driven workflow state, validation boundaries, and human review seams; implementation is in progress
PythonFastAPIWorkflow GraphsQueue-backed Jobs
Read case study