AI production intelligence for AEC
Claude Code for architecture, engineering, and construction, with shared context across the value chain, bringing massive savings across multi-hundred-million-dollar projects.
Self-serve by design: your team drives it, from question to reviewed output.
What we're building
Project Cornerstone is building a private, permissioned AI production layer for architecture, engineering, and construction. One shared context for every party on the project, from developer to trades.
The whole value chain
Each party works from the same permissioned context.
Developers. One workspace for the whole project, fewer surprises in the field.
Architects. More projects with the same team. Less error tax.
Engineers. Assumptions confirmed before they harden, first passes ready for review.
GCs. The design intent behind the drawings, on demand.
Subs and trades. Scoped answers in the field, drawn from the same facts.
Designed so the value grows as more of the chain joins.
On top of your tools
It sits on the tools the industry already uses. Revit, ACC, and PDFs stay the source of truth.
Generic AI tools have never seen your work. Project Cornerstone is built to answer from it, with citations.
- Precedent retrieval: start from what the firm already built
- Drawing QA: a checked baseline before any set goes out
- Code context: constraints surface while change is cheap
- Consultant checks: assumptions confirmed before they harden
- Scoped handoff: downstream teams see only what they need
Self-serve by design. No waiting on specialists to run a workflow.
The goal is not to replace architects, engineers, contractors, or tradespeople. The goal is to give them a trusted AI layer that preserves context, accelerates repeated work, and supports human-reviewed decisions across complex projects.
Demand swings. Payroll can't.
Work arrives in waves, and firms staff for the trough.
Every new project rebuilds context someone in the chain already has.
With elastic inference, a lean team flexes through the peak, and labor starts to behave like a variable cost.
"We would not have to staff up and cut back every time the market turns. For a firm our size, that is the game changer."
CFO, US multifamily architecture firm
Workflow packs
Up to 30% of a phase's spend is work that repeats from past projects. Packs recover it.
- CD-to-DD pull-forward. Prior detail work drafted into the current set.$52.5K to $125K modeled savings per project
- Engineering draft outputs. First-pass deliverables routed to engineer review.$75K to $160K modeled savings per project
- GC and trade estimates. Quantities and first passes for estimator review.$87.5K to $250K modeled savings per won project
- Drawing QA. Small errors caught before the set goes out.being measured in production trials
Modeled on a benchmark composite project · assumptions available on request
Define. Configured around your standards and review gates.
Run. On live project work, as often as needed.
Review. Every output reaches the right reviewer first.
Packs are designed to run self-serve, with expert support when you want it.
Your knowledge stays yours
Each party's data and outputs stay that party's property. Nothing trains public models without permission.
Access is scoped by source, role, and project. Answers keep their citations.
Sharing across the chain is permissioned down to each source.
| Source | Architect | Engineer | GC | Trade |
|---|---|---|---|---|
| Firm standards | Full within role scope | Not shared | Not shared | Not shared |
| Model and drawings | Full within role scope | Scoped view | Scoped view | Scoped view |
| Consultant inputs | Scoped view | Full within role scope | Scoped view | Not shared |
| Review history | Full within role scope | Scoped view | Not shared | Not shared |
| Construction evidence | Scoped view | Scoped view | Full within role scope | Scoped view |
Where the work stands
Now. Completing a paid assessment with a design-partner architecture firm.
Next. A pilot on a live project, architecture side first.
Goal. The full value chain on the project, with developer buy-in.
Work with us
We want to hear from:
Firms, developers, GCs, and trades with repeated production work
Investors in vertical AI and AEC automation
Technical co-founder and founding engineers
Also hiring: AI and full-stack engineers, computational designers, BIM experts, and FDE-style builders.
An email gets you a working session on one of your live projects.