CoCivil

Inspiration

The inspiration originated from Elliot's personal experience: his father wanted to build a garage but quickly discovered the absolute nightmare of municipal regulations and infrastructure connections. He realized that if a homeowner struggles with scattered local zoning by-laws and basic pipe tie-ins, professional civil engineering and planning firms must face a catastrophic operational ceiling. This sparked the vision for a tool to instantly parse rigid local codes and eliminate the manual research bottleneck for both property developers and civil engineers.

What it does

CoCivil operates as a Site Servicing Feasibility Copilot for civil engineers and property developers. It transforms a plain-English development query into a structured and source-backed analyze package. The system seamlessly combines deterministic zoning compliance, 3D massing visualization, and infrastructure policy checks. It specifically helps civil engineers instantly validate municipal water system restrictions and pipe regulations to drastically accelerate the creation of early-stage Functional Servicing Reports (FSR).

How we built it

We engineered a deterministic compliance engine to ensure absolute reproducibility without relying on AI for physical rule generation. We constrained the AI using strict grounding instructions to only cite sources explicitly provided within the context. The architecture utilizes PostGIS for complex spatial queries. This allows us to resolve parcel boundaries against municipal water systems and infrastructure overlays in milliseconds. We integrated MapLibre GL for the 3D map environment and Konva for the rapid 2D site editor. We also deployed Celery asynchronous pipelines to handle intensive plan generation tasks without risking request timeouts.

Challenges we ran into

Our primary strategic challenge was identifying the true industry pain point: the core problem is not merely saving research hours, but rather fixing the dangerously high error rate in feasibility models built manually in Excel. Furthermore, we encountered severe technical hurdles when scraping data from government sites. We had to build resilient ingestion tasks to pull from the Toronto Open Data CKAN API for building permits, Committee of Adjustment applications, and water infrastructure policies after facing aggressive access blocks.

Accomplishments that we're proud of

We successfully mapped the complex policy stack of the Greater Toronto Area into deterministic rules. This now includes rigid municipal water system policies and pipe connection regulations alongside recent provincial legislation like Bills 23, 185, and 60. We are incredibly proud of our integrated environment. Civil engineers can now instantly validate site servicing feasibility and catch regulatory violations before ever opening AutoCAD to design physical pipes.

What we learned

We learned that generative AI is fundamentally unsuited for regulatory and engineering compliance if left unconstrained. Compliance is not an opinion: it requires absolute deterministic reproducibility. We realized that enforcing strict safety preambles and citation verifiers is mandatory to prevent hallucinations. This is the only way to establish an audit trail that engineering professionals can actually defend in formal municipal submissions.

What's next for CoCivil

The immediate next step is integrating live APIs for the Application Information Centre, Ontario Land Tribunal, and CanLII to automate precedent research entirely. We also plan to expand our data ingestion to cover deeper civil engineering heuristics across multiple jurisdictions. Finally, we will finalize a governance-stamped PDF export feature so engineering consultants can instantly download audit-ready Functional Servicing Reports and compliance packages.

Tools & Libraries

Artificial Intelligence & LLMs

Google Antigravity: Autonomous AI agent used as a pair-programmer to rapidly build out the codebase, translate civil/zoning policies into structured skills, and orchestrate the full-stack architecture.
Google Gemini API: Core inference engine powering multimodal document analysis (reading CAD/DXF pipelines, PDF site plans, and dense municipal by-laws) and civil engineering calculations (e.g., Hazen-Williams flow rates and structural risk assessments).
RAG Infrastructure: Built to ingest and retrieve context from Ontario planning legislation, Toronto ECS (Engineering & Construction Services) standards, OPSS, and AWWA manuals.

Frontend & Rendering (Client-Side)

React 19: Core UI framework.
Vite: Extremely fast frontend build tool.
Three.js / React-Three-Fiber / React-Three-Drei: For the immersive 3D WebGL/WebXR environment to visualize underground pipeline geometry and above-ground building massing/shadows directly in the browser.
MapLibre GL JS: High-performance, WebGL-based vector map rendering for the geospatial parcel and infrastructure viewers.
Konva / React-Konva: Used for the 2D HTML5 canvas rendering (e.g., interactive floor plan editors and vector manipulation).
Auth0 (react-auth0): Enterprise-grade identity management, handling secure JWT authentication and role-based access control (RBAC).

Backend & APIs (Server-Side)

FastAPI: High-performance async Python web framework used for the core API server.
Uvicorn: ASGI web server implementation for Python.
SQLAlchemy 2.0 (Asyncio): Core ORM handling database models and asynchronous connections.
PyMuPDF & ezdxf: Powerful parsing libraries used to extract spatial metadata from uploaded PDF site plans and civil CAD/DXF files.
Pydantic: Data validation and settings management tailored for the API schemas.

Database & Geospatial Infrastructure

PostgreSQL: The core relational database engine.
PostGIS & GeoAlchemy2: Advanced geospatial extensions to store, query, and manipulate 2D and 3D geometries (lot footprints, pipeline networks).
pgvector: Postgres extension used to store high-dimensional embeddings generated by Gemini for fast semantic retrieval of zoning and civil policies.
Asyncpg: High-performance async database driver for Python.
Alembic: Database migration tool used alongside SQLAlchemy.

Cloud & DevOps

Docker & Docker Compose: Containerization of the API, databases, and worker queues to ensure parity between local development and production.
Redis: In-memory data store used for caching and managing async background tasks.
Neon Serverless Postgres: Scalable, serverless Postgres platform used for hosting the heavy geospatial database.
Railway: Platform-as-a-Service (PaaS) used to host and deploy the backend containerized workloads.

* Amazon Web Services (AWS / Boto3): S3 used for secure storage of uploaded client CAD and PDF files.

Hackathon Track Info

1. [MLH] Best Hack Built with Google Antigravity Instead of manually writing boilerplate code, scouring documentation, and iterating through trial-and-error to create a complex due-diligence platform, Google Antigravity served as an autonomous AI-pair programmer. It rapidly translated Ontario's complex planning policies and dense civil infrastructure standards (OPSS, AWWA, Toronto ECS) into structured "skills" and seamlessly orchestrated our full-stack application (FastAPI + React). It dynamically solved challenging web development tasks like integrating 3D WebXR features for subsurface infrastructure and complex CAD/DXF data parsing in a fraction of the time.

2. [MLH] Best Use of Gemini API Target users: Real Estate Developers, Civil Engineers, Investors, and Municipal Planners.

What it does differently: CoCivil goes beyond basic chatbots. We use the Gemini API to perform intensive, long-context analysis of dense Ontario planning legislation, zoning by-laws, and civil engineering standards. Gemini processes multimodal inputs—such as raw property data, PDF site plans, and infrastructure CAD/DXF files—to generate precise outputs like Variance Justifications and Pipeline Condition Assessments. It uses AI to instantly cross-reference Hazen-Williams flow rates and pipe break probabilities based on material data, turning weeks of manual engineering analysis into an instantaneous operation.

Future scalability: The system can be scaled to analyze even larger multimodal inputs using Gemini 1.5 Pro (e.g., massive municipal CAD files, ground-penetrating radar data, and historical satellite imagery) to cross-reference proposed developments and underground utility conflicts automatically.

3. [MLH] Best Use of Auth0 Target users: Enterprise real estate firms, engineering consultants, legal professionals, and individual investors.

What it does differently: High-stakes land-development and critical public infrastructure data is sensitive. Auth0 provides enterprise-grade identity management out-of-the-box, allowing us to enforce strict role-based access control (RBAC). Planners have access to draft applications and civil designs, while investors only view the final feasibility dashboards. Auth0 allowed us to securely authenticate without managing complex session states ourselves.

Future scalability: Auth0's scalable architecture makes it easy to integrate with enterprise Single Sign-On (SSO) for municipal governments, multi-factor authentication for sensitive engineering deals, and machine-to-machine (M2M) authentication as we open our zoning/civil logic to external APIs.

4. Google - Build with AI Track Target users: Real Estate Developers, Civil Engineers, and Urban Planners in Canada.

What it does differently: CoCivil removes the bottleneck in land development and public works. Instead of paying thousands of dollars and waiting months for preliminary consultant reports, CoCivil leverages AI to instantly process regulatory documents, parse underground pipeline networks from DXFs, compare them to a site's parameters, and flag compliance or structural risk issues (like asbestos cement pipes or end-of-life cast iron). We use AI not just for text generation, but for structured decision-making that governs physical land use and critical infrastructure.

Future scalability: We plan to fine-tune specialized models on historical Committee of Adjustment decisions and municipal watermain break data (using RAG) to predict the probability of a variance approval and optimize lifecycle replacement costs for civil assets.

5. Most technically complex AI hack Target users: Sophisticated users like architects, civil engineers, and urban strategists who require deep data linkage.

What it does differently: The sheer technical depth of CoCivil sets it apart. The platform orchestrates a multi-step pipeline: extracting spatial and textual data from PDFs and subsurface DXFs, using specialized "skills" (such as Ontario statutory tests and Civil Engineering pipe specifications) to parse legal/technical text via LLMs, evaluating physical massing and underground pipe networks in a 3D WebXR environment, and rendering real-time, compliant engineering metrics. Integrating background tasks/workers, async pgvector geospatial queries, Auth0, and 3D WebGL rendering with a central AI orchestrator is a heavyweight engineering feat.

Future scalability: The infrastructure is containerized and built on robust async patterns (FastAPI + asyncpg), designed to handle massive concurrent spatial data processing and automated parameter-sweeps for optimal building designs and pipe routing across entire cities.

6. SPUR Founder Track - Build a Real Canadian Startup Target users: Canadian real estate developers, "missing middle" housing builders, civil engineering consultants, and property investors.

What it does differently: Canada is dealing with a severe housing crisis and an aging infrastructure deficit, exacerbated by municipal red tape. CoCivil is a hyper-localized, commercially viable startup that directly solves this bottleneck. By providing developers with "As-of-Right Eligibility" and municipalities with instant "Infrastructure Condition Assessments" on day one, we significantly de-risk housing and civil projects. It targets a real, expensive, and pressing Canadian problem with a market-ready solution.

Future scalability: After dominating the Ontario market, the underlying rules engine and AI schema can be adapted to B.C.'s recent zoning overhauls or cross-border markets. We plan to monetize via a SaaS subscription model for developers or a per-parcel screening fee for municipal public works departments.

7. Best Virtual Reality & WebXR Hack: Immersive Experiences for the Open Web Target users: Community stakeholders, city councillors, civil engineers, and developers visualizing site massing and infrastructure.

Why immersion matters / What it does differently: Seeing a "building height limit of 15m" or a "300mm cast-iron watermain" on paper means very little to the average person. Immersive Tech matters because land use and civil engineering are inherently physical. Using standard web technologies (react-three-fiber / WebXR), CoCivil brings proposed zoning massings and hidden subsurface pipeline networks to life. Users can view the 3D footprint, shadows, and underground pipe envelopes directly in the browser—democratizing the visualization of urban changes above and below ground.

Future scalability: The WebXR viewer can scale to support full VR headsets, allowing community members at town hall meetings to virtually stand on their street and see exactly how a proposed mid-rise development—and the underlying civil infrastructure required to support it—will impact their sun, shadow, and neighborhood feel.