Skip to main content

Engineering software that matters.

Environmental science platforms, AI automation, smart infrastructure. Fort Collins, Colorado.

Scroll
By the Numbers
30+
Organizations served
10+
Countries
6
Domain specializations
5+
Active production platforms
What We Build

Deep domain expertise.

01

Environmental Science & Climate Technology

Greenhouse gas emissions modeling, soil carbon quantification, and agricultural management simulation. We integrate biogeochemical models like DayCent and Landscape DNDC with modern cloud platforms to make complex science accessible.

02

AI-Powered Business Intelligence

Self-improving knowledge engines that turn manual, knowledge-intensive processes into structured automations. Our Intelligence Node architecture combines deterministic classification with LLM fallback and human-in-the-loop learning.

03

Geospatial & GIS Applications

PostGIS spatial databases, MapLibre GL interactive mapping, Cloud Optimized GeoTIFFs, and dynamic tile serving. From field boundary drawing to zonal statistics at 30m resolution across entire states.

04

Smart Home & IoT Infrastructure

Building automation, smart meter management, and home commissioning lifecycle systems. 8+ years integrating Siemens Desigo BMS, CopperLabs utility metering, and IoT device provisioning at community scale.

05

Mobile & Marketplace Platforms

React Native cross-platform applications with Expo managed workflows, marketplace bid economies, Stripe payment integration, and OTA update deployment. Database-driven service catalogs that scale without app rebuilds.

06

Enterprise & Operations Software

Multi-tenant SaaS platforms, complex workflow automation, background job processing, and multi-API integration orchestration. From county filing pipelines processing 500+ records in seconds to role-based admin portals.

Selected Work

Enterprise systems at scale.

Environmental Science

Cloud-Native Agricultural Emissions Platform

Challenge

Agricultural researchers needed to run complex biogeochemical simulations but existing tools required desktop installations, manual data formatting, and deep technical knowledge of model internals.

Approach

Built a 4-tier microservices platform connecting an interactive mapping frontend to model orchestration services. Users draw field boundaries, enter management practices, and receive emissions projections — the system handles model translation, execution, and results visualization. Supports DayCent and Landscape DNDC engines with a plugin architecture for additional models.

9 repositories, 4-tier architecture60+ frontend components, 102+ test suitesMulti-language support (English, Spanish, Danish)HECVAT Lite compliant for university deployment
AI Business Intelligence

Enterprise Document Intelligence & Automation Engine

Challenge

A global building technology company needed to extract structured data from 50+ page vendor inspection PDFs — a manual process taking 8 hours per report across multiple report formats and vendor-specific terminology.

Approach

Deployed an on-premise Intelligence Node with multi-path document extraction (rule-based parsing for 99.8% of PDFs, Claude vision API fallback for scanned documents). Built a three-tier classification engine with confidence scoring and a human-in-the-loop learning loop — every technician correction automatically improves the knowledge base for future processing.

8 hours reduced to 30 minutes per report99.8% extraction accuracy100% classification accuracy (649-device test case)Zero external API dependencies for core processing
Geospatial

Conservation & Compost Application Planning Tool

Challenge

Conservation scientists needed a way for landowners to assess soil organic carbon and water capacity at parcel level, with decision support for compost application planning across California counties at 30m resolution.

Approach

Built a hybrid rendering geospatial application combining client-side vector tiles (PMTiles via MapLibre GL) with server-side raster WMS (GeoServer). Node.js backend orchestrates Python GDAL processes for raster operations. Includes point-click analysis, area-of-interest drawing, zonal statistics, and 1-30 year benefit projections.

150,000+ parcels per county at 30m resolution5 Docker containers, self-hosted deployment$100K budget, 4-month deliveryBilingual interface (English/Spanish)
Smart Infrastructure

Enterprise IoT Community Management Platform

Challenge

A 3,200+ home smart community needed a unified platform to manage the complete lifecycle from county lot filing through 2-year post-closing homeowner support — coordinating builders, technicians, and 15,000+ IoT devices.

Approach

Built a hybrid enterprise architecture combining an ASP.NET Core web platform with a Python CLI filing pipeline. The system manages 4-phase home commissioning, automated lot filing (500+ homes processed in under 30 seconds), drag-and-drop technician scheduling, and real-time IoT utility monitoring across gas, electric, and water meters.

3,267+ homes actively managed15,110+ IoT meters tracked in real-time19-20 active builders coordinated6 external API integrations orchestrated
Product

The Intelligence Node

You know that one person on every team who just knows how everything works? The one everyone asks before checking the manual? The Intelligence Node captures that knowledge and makes it operational — a self-improving engine that gets smarter every time someone uses it.

Not a chatbot. Not a search engine. A structured knowledge system with domain-specific classification, deterministic processing, and learning loops that compound over time.

Domain-Specific AISelf-ImprovingKnowledge CaptureProcess AutomationFlexible DeploymentCompound Intelligence
01

Knowledge Ingestion

We immerse in your domain — standards, classifications, vendor terminology, operational rules. This becomes the Intelligence Node's reference data layer.

02

Workflow Automation

Manual processes become structured automations. Document extraction, classification, validation — each workflow uses deterministic rules first, AI fallback for edge cases.

03

Human-in-the-Loop Learning

When the system encounters low-confidence results, your team reviews and corrects. Every correction feeds back into the knowledge base automatically.

04

Compounding Intelligence

The system gets smarter with every workflow processed. New automations reuse 80% of existing domain knowledge out of the box. Competitors start at zero.

Who We Work With

Research, enterprise, and everything between.

Government & Research

  • USDA NRCS
  • USDA FAS
  • CARB
  • NCAT
  • Colorado State University
  • UNEP/GEF

International Academic

  • Aarhus University
  • University of Bern
  • University of Hawaii
  • University of Leicester
  • IDRC

Foundations & Conservation

  • Novo Nordisk Foundation
  • Point Blue Conservation Science
  • FFAR
  • Soil Health Institute
  • SEGES

Enterprise & Commercial

  • Siemens
  • Walmart
  • National Grid
  • John Deere

Agriculture & Carbon

  • Indigo Ag
  • NORI
  • SoilMetrics

Technology & IoT

  • CopperLabs
  • iBlinds
  • Sterling Ranch
About

Born in research. Built for production.

The Origin

Axios grew out of Colorado State University's Research Software Facility, where our founder spent 14 years building software for environmental science — rising from engineer to director. The work: nationally recognized platforms for the USDA and research institutions worldwide. That's not a pivot into climate tech. It's the origin story.

Fort Collins sits in Colorado's Front Range research corridor — home to NOAA and NIST in Boulder, NREL in Golden, multiple USDA research facilities, and Colorado State University. We've been embedded in this ecosystem for over a decade, and it shaped how we think about building software for science and government.

“Axios” means “worthy” in Greek. We chose it because we believe the problems we work on — and the people who bring them to us — deserve engineering that takes them seriously.

Philosophy

Honest and Sharp. Quick and Nimble. Fun.

We don't just write code — we understand the science, the operations, and the data behind the systems we build. When we say we work in agricultural emissions modeling, we mean we've spent a decade integrating biogeochemical simulation engines. When we say IoT infrastructure, we mean 3,200+ homes with 15,000+ meters tracked in real-time.

Founder

Kevin Brown

Founder & President / Chief Software Architect

15 years at Colorado State University's Research Software Facility, rising from engineer to director. Original architect of nationally recognized software platforms for the USDA, deployed across 10+ countries.

Leads architecture and delivery across environmental science, AI business intelligence, and smart infrastructure. Principal investigator on international research collaborations spanning three continents. Built and shipped production systems for USDA, Siemens, and university research programs worldwide.

Technology

Multi-platform, production-grade.

Frontend

  • React 17–19
  • React Native / Expo
  • Next.js 14–15
  • TypeScript
  • Tailwind CSS
  • MapLibre GL

Backend

  • NestJS
  • ASP.NET Core
  • FastAPI
  • Supabase Edge Functions
  • Express
  • Flask

Data & AI

  • PostgreSQL / PostGIS
  • Redis
  • SQLite
  • Anthropic Claude API
  • n8n Orchestration
  • DayCent / DNDC Models

Cloud & Infra

  • Google Cloud Run
  • Google Cloud SQL
  • Vercel
  • Supabase
  • Docker
  • GitHub Actions

Mobile

  • React Native 0.43–0.81
  • Expo SDK 54
  • EAS Build / Update
  • Stripe SDK
  • Firebase
  • Sentry

Integrations

  • Stripe Payments
  • Auth0
  • SendGrid
  • CopperLabs IoT
  • BIM 360
  • GeoServer

Got a complex problem? Good.

We scope projects honestly and estimate for free. If we're not the right fit, we'll tell you — and probably point you in the right direction.

kbrown@axiossoft.com — Fort Collins, Colorado