How I built an AI-native system to reconstruct, validate, and package a complete transport model output — and ship it as a production tool to the customer.
Developed for Netivei Ayalon as part of the Beer Sheva metropolitan transport model certification process, enabling rigorous quality assurance of model outputs before government submission.
“You can't approve a model you can't verify. This system makes verification fast, repeatable, and transparent.”
Transport model outputs are complex — dozens of tables, thousands of rows, multiple time periods. Manually checking them against targets takes weeks and is error-prone. I built a system that does it automatically, and ships as a ready-to-use tool.
The system reads raw model outputs — road network assignments, transit ridership, route data — and reconstructs each required report table using the exact formulas from the model's specification document.
Each reconstructed table is automatically compared against the official target. The system flags every mismatch — missing rows, extra rows, value differences above tolerance — and produces a detailed diff report.
A professional Streamlit dashboard lets an analyst review any table, switch between time periods (AM, off-peak, PM), filter by match status, and inspect individual cell-level differences with smart color coding.
The entire system was packaged as a standalone deliverable and handed to the customer — including all inputs, scripts, GUI, and documentation — so they can run it independently at any time.
A walkthrough of the reconstruction dashboard and validation interface.
The reconstruction engine, test suite, GUI, and packaging workflow were all built using AI-native development with Claude and Codex. Not just code generation — full-cycle development: architecture design, iterative implementation, automated testing, and production hardening. This is the workflow I teach.
Transport model validation is a legal and contractual requirement before major infrastructure decisions. A system that does it automatically — and produces a paper trail — replaces weeks of manual analyst work and eliminates the risk of undetected errors in the outputs that decision-makers rely on.
Want AI-native tooling like this for your transport project?