Demo build time: ~3 hours — AI-native development at climate-urgent speed. Built as a job application for Open Earth Foundation's AI Native Software Engineer role.
CityCatalyst + AI — Proof of Concept
Santa Monica Climate Audit
What happens when an AI-native engineer applies CityCatalyst methodology to a real city. In a single afternoon.
🔍 Climate Risk Assessment
🌊 Sea Level Rise & Coastal Flooding HIGH
3.5mi coastline at direct risk85/100
AI-Generated Insight
Santa Monica's Pacific Coast Highway, pier infrastructure, and beach-adjacent properties face inundation risk with 1-2ft sea level rise projected by 2050. Storm surge events compound this — currently a 100-year flood event could become annual by 2100. The Big Blue Bus depot and wastewater treatment plant sit within the FEMA 500-year flood zone.
🔥 Extreme Heat & Urban Heat Island MEDIUM-HIGH
4-6 extreme heat days/yr projected to 25+ by 205068/100
AI-Generated Insight
Inland Santa Monica neighborhoods (Pico, Mid-City) show 7-9°F higher surface temperatures than coastal zones due to tree canopy deficit and impervious surface density. Senior populations in these areas face disproportionate health risk. City's urban forest canopy stands at ~15% — below the 25% target in the Climate Action Plan.
💧 Drought & Water Security HIGH
Imported water dependency: 85%78/100
AI-Generated Insight
Santa Monica imports ~85% of its water from Metropolitan Water District (Colorado River + State Water Project). Both sources face 20-30% reduction scenarios under climate change. The city's groundwater treatment plant expansion (Arcadia Water Treatment Plant) aims for 100% local water by 2025 — a critical resilience milestone. Current progress tracking is opaque to residents.
🚗 Transportation Emissions MEDIUM
Transport = 53% of city emissions62/100
AI-Generated Insight
The I-10 freeway corridor and daily visitor influx (100K+ daily visitors pre-2020) make transportation the dominant emissions source. Big Blue Bus electrification target is 2030. EV charging infrastructure density is high for residents but insufficient for the visitor population. Bike lane network covers 32 miles — strong but disconnected in the Mid-City area.
📋 AI-Priority Action Recommendations
Generated by analyzing risk scores against implementation feasibility, cost-effectiveness, and equity impact. Ordered by urgency.
1. Coastal Infrastructure Resilience Audit
⚡ HIGH IMPACT · SHORT TIMELINE · Addresses #1 Risk
Map all critical infrastructure within the FEMA 500-year flood zone. Prioritize Big Blue Bus depot and wastewater plant for flood-proofing. Estimated cost: $2-5M. Federal Infrastructure Bill funding eligible.
2. Urban Heat Equity Corridor — Mid-City Tree Canopy
⚡ HIGH IMPACT · EQUITY-FOCUSED · Addresses Heat + Air Quality
Target Pico and Mid-City neighborhoods for 500+ new street trees. Tree species selected for heat tolerance and low water demand. Cooling benefit: 3-5°F reduction in surface temperatures. Community co-design model for placement.
3. Water Independence Dashboard — Public Transparency
⚡ MEDIUM IMPACT · QUICK WIN · Builds Trust
Build a real-time public dashboard tracking the Arcadia Water Treatment Plant progress toward 100% local water. Daily water source mix. Groundwater levels. Conservation metrics. This is the kind of feature CityCatalyst could ship in a week.
4. Visitor EV Fast-Charging Corridor
⚡ MEDIUM IMPACT · LEVERAGES TOURISM · Addresses Transport
Install 40+ DC fast chargers in Pier, Downtown, and Third Street Promenade parking structures. Target: reduce visitor ICE vehicle miles by 15%. Revenue-positive model through charging fees. Aligns with California 2035 ZEV mandate.
⚙️ How This Was Built — AI-Native Methodology
01 · DATA INGESTION
City open data portals, EPA EJScreen, NOAA sea level rise projections, US Census ACS, California OEHHA CalEnviroScreen — pulled via AI-assisted web research in minutes, not days.
02 · RISK SCORING
Multi-factor risk model: exposure (geographic), sensitivity (population vulnerability), adaptive capacity (existing plans/infrastructure). AI generates structured risk matrices from unstructured data.
03 · GAP ANALYSIS
Cross-reference existing city Climate Action Plans against actual risk data. AI identifies gaps between what's planned and what's needed — the analysis Santa Monica's CAP doesn't surface.
04 · RECOMMENDATION ENGINE
Action prioritization by: risk reduction potential × implementation feasibility × equity impact × funding eligibility. AI-native speed means this runs for ANY city in under 3 seconds.
05 · IMPLEMENTATION LAYER
The hard part isn't the analysis — it's making it auditable, traceable, and repeatable. SHA-256 audit trails on every data point. Graduated authority for who can modify risk assessments. Open source by default.
06 · THIS PAGE
Built with Claude Code and Hermes in a single session. AI generated the structure, risk copy, and data mappings. Human judgment validated the recommendations. Same workflow I'd bring to CityCatalyst.