Context AI, OpenEPA & Calculation Editor

After building Immutably™'s Knowledge Graph technology to create industrial digital twins, we had a powerful insight infrastructure. Energy clients were using it to model entire facilities, but the KG capabilities (ontology mapping, sub-second queries, data provenance) could do so much more.

We spotted the opportunity: EPA's GHGRP emissions data was public but difficult to use. Researchers spent weeks wrangling Excel files, journalists couldn't cite sources, and custom calculations had zero reproducibility. Our KG technology could solve all three problems at once.

I led design prototyping for OpenEPA using rapid high-fidelity prototyping to validate conversational UI patterns for data queries. Conducted user testing with 15+ researchers validating design hypotheses: natural language queries with structured data responses, citation visibility, and progressive disclosure of complex emissions data. Design validation informed engineering architecture decisions and feature prioritization.

In parallel, I designed Context AI microservice UX for energy sector client intelligence. Using Vue 3 + TypeScript, I created production-ready design prototypes for AI-powered onboarding flows reducing prep time from 2+ hours to 60 seconds. Design prototyping with mock services unblocked parallel engineering development, saving 3 weeks per product cycle through validated design direction.

With the POC validated, we built the full OpenEPA platform infrastructure. I designed the EPA data ingestion pipeline with version tracking where every emissions report is timestamped with its EPA source URL and release date. This wasn't just about loading data; it was about creating an audit trail that researchers and journalists could trust.

We integrated ArcadeDB as our Knowledge Graph store, leveraging the same ontology-mapping capabilities we'd built for Immutably™. The result: sub-second queries across 2,800+ facilities and 15 years of emissions history. Researchers could compare facility emissions trends, identify geospatial hotspots, and benchmark Top/Bottom 5 emitters, all with full data provenance showing exactly where each number came from.

With the EPA data pipeline running, we deployed Context AI on Azure to power the intelligence layer. The challenge was connecting AI models to our Knowledge Graph so they could answer complex emissions queries with full citations. We used Azure OpenAI Service with GPT-4, building a custom integration layer that translated natural language questions into KG queries and synthesized responses with EPA source attribution.

The Context AI microservice became the bridge between our KAG infrastructure and both OpenEPA (for emissions Q&A) and the energy sector AE dashboard. For OpenEPA, researchers could ask "Which Texas refineries increased emissions most from 2020-2023?" and get cited answers with EPA report URLs. For the AE dashboard, Context AI analyzed client KG data to generate company intelligence in under 60 seconds.

Automated data is powerful, but we found an even bigger opportunity: enabling researchers to create industrial workflows using their own methodologies. I designed the Calculation Editor (Abacus) to let users build custom emissions intensity calculations (per MWh, per ton of product, per capita) with full formula transparency and methodology documentation.

The key was our custom ontology. Drawing on industrial best practices and client methodologies from energy companies, we designed an ontology that mapped EPA emissions data to production metrics, financial data, and operational parameters. Researchers could now normalize emissions by facility output and compare apples to apples, something EPA's raw data didn't support out of the box.

As we prepared for OpenEPA's public launch, we formalized our team structure. We established an R&D office in Amsterdam with a small, focused team tracking work through a Kanban board and running bi-weekly retros. This wasn't just about process but about culture. We transitioned from an Engineering-led approach (build features, ship code) to Product-led (solve user problems, measure impact).

This transition actually started earlier with my work on the Immutably™ platform, where I shifted the company from feature-driven development to user-research-driven product strategy. With OpenEPA, Context AI, and Calculation Editor, we applied those same lessons: validate with users, ship MVPs fast, iterate based on feedback, and measure everything.