RESOURCES
How we think about construction intelligence.
Methodology, architecture and governance — written for the people who have to defend the decision, not just approve the software.
The Project World Model
Why construction AI fails without a shared semantic layer for entities, activities, evidence, risks and actions — and what that layer has to contain.
Read · 2 min →Stop Reporting. Start Forecasting.
A single completion date is a claim with the uncertainty deleted. What P10/P50/P90 forecasting actually requires from your project data — and what it gives back.
Read · 2 min →Governing AI Agents on Capital Projects
Autonomy is not the goal. A governance model for construction agents — permissions, approval gates, evidence requirements and the audit trail that makes them defensible.
Read · 2 min →Evidence-First Retrieval
Why a chatbot over a document store is the wrong architecture for construction, and what has to replace it before an answer can be trusted.
Read · 2 min →