The construction industry loses $1.
6 trillion annually to inefficiencies — not because people are careless, but because critical knowledge is trapped in PDFs, transcripts, and scattered systems.
Every new project starts from scratch.
We're building the opposite: an AI co-worker that extends the Projektsteuerer (the person who runs complex construction projects), while every project makes our system measurably better.
The moat isn't the model — it's the compounding project memory no competitor can replicate.
Pre-seed led by Realyze Ventures — LPs include Zech and other major European construction groups.
Co-investors: D11Z (the family office behind Aleph Alpha) and the CDTM Venture Fund (backed by 300+ CDTM alumni including founders of Personio, Alasco and the Technical Director of DeepMind).
Our software is running today on a major autobahn construction program and an S-Bahn transit program — multi-year timelines, hundreds of thousands of pages of specs, protocols, and communications.
Real consequences when we get it wrong.
Tasks Two hard problems.
All production.
AI-native project management, not a chatbot on top of PDFs The construction industry doesn't need another chat wrapper around GPT.
It needs project management software where AI runs in the background — through cronjobs, proactive alerts, and task dashboards — not in a sidebar chat window.
The hard product question is how AI shows up: when as silent background automation, when as a surfaced recommendation the PM approves, when as a fully delegated task the user only reviews after the fact.
Extending harness engineering all the way to the UI Agent harnesses don't stop at the backend.
A multi-step agent run that streams tokens, calls tools, hits failure modes, and recovers gracefully needs a frontend that makes all of that legible in real time.
You'll plumb Vercel AI SDK streams from our agent layer straight into the component tree — streaming, tool-call traces, interrupts, partial renders, graceful failur.