What
SuperHive by ai71 was an AI-powered construction intelligence suite with specialized apps across the project lifecycle — planning, design, execution, and monitoring.
SuperHive was discontinued in 2026. This is a record of what it did and what I worked on.
I worked as a Product Engineer on the compliance side of the platform: Analyze Studio, an AI-driven compliance engine for CAD and BIM files that detected regulatory issues and internal design mismatches — spanning architecture, structural, and computational design workflows.
Why it matters
Construction projects are slowed down by manual processes, fragmented tools, and inconsistent data. On the public numbers alone, up to 40% of project time goes to repetitive, non-value-adding tasks, and around 80% of project data is unstructured — driving delays, rework, and cost overruns.
The opportunity is to bring AI and structured, data-driven workflows to a domain that has historically relied on scarce expert time and manual review.
What I did
Bridging product and engineering. I acted as a cross-functional bridge between product and engineering, coordinating ML engineers to align technical execution with the product vision.
Building the AI-powered BIM platform. I helped develop the platform that integrated large language models and generative AI into domain-specific workflows across architecture, structural analysis, and computational design — owning framework definition, testing strategy, debugging pipelines, and process streamlining.
Applied research & rapid prototyping. I ran applied research and rapid prototyping of emerging technologies, translating experimental findings into production-ready solutions that met client requirements and real-world technical constraints.
My role
Product Engineer — worked across the team to frame the problem, shape buildable slices, and validate with real usage, so technical depth showed up as clarity in the product.
Domain grounding (BIM & AEC) — kept the roadmap anchored in how models are actually authored, exchanged, and reviewed in practice.
Focus areas
- Product ↔ engineering alignment
- LLM & generative-AI integration into AEC workflows
- Testing strategy & pipeline debugging
- Applied research → production