For architect and construction entrepreneur Al Dram, the idea behind Blueprints AI began nearly two decades ago, long before generative artificial intelligence became a mainstream tool. As a college student, Dram wrote a final thesis about software that could generate design documents for school buildings. He was studying architecture, following in the footsteps of his parents and grandfather, but technology intrigued him more than traditional practice. The problem was that the technology his thesis imagined did not yet exist.
Then in November 2022, OpenAI released ChatGPT, the generative AI chatbot built on large language models. Dram said that moment changed the calculus. His old idea suddenly seemed much more possible. Within six months, he launched the concept of Blueprints AI, a startup that uses AI to produce code-compliant and permit-ready architectural construction blueprints in minutes from a 2D sketch or PDF.
Dram officially incorporated Blueprints AI in 2025 in Santa Monica with co-founder Coco Cao. The company was selected for a 2026 early-stage startup showcase at a major San Francisco technology conference running Oct. 13 to 15. It is using the event to unveil a more capable second-generation version of its software.
A long route from architecture school to construction
Between the thesis and the startup, Dram built a career across architecture, digital design and construction. He earned bachelor's and master's degrees in architecture from the University of Tehran and completed two years of PhD coursework on digital design at the European Graduate School in Switzerland. He moved to the United States and opened an architecture firm called Drams Design-Build in 2018. After obtaining a general contractor's license, he added a construction business in 2021.
Dram said he should have been satisfied. He was not. He wanted a larger impact than individual projects could provide. He described his motivation as saving hours and energy for people who perform the same tasks over and over. That focus on repetitive work became the foundation of Blueprints AI.
What the software does
Blueprints AI's core promise is speed and coordination. Architectural construction documents are not simple sketches. They include dimensioned plans, elevations, sections, schedules, details and coordination among disciplines. Permitting authorities review these documents for compliance with building codes, zoning, fire safety, accessibility, energy, structural and other requirements. Drafting and revising those documents is labor-intensive, and changes in one part of a project can ripple across many sheets.
The company's first-generation software produces architectural construction documents and costs between $3,200 and $8,500 a month, depending on the plan. Custom enterprise pricing is also available. The second-generation software is broader. Customers can start with a description or sketch of a project and create blueprints for every aspect of a building at once, including architecture, structural, mechanical, electrical, plumbing and interior design. Version 2 also allows users to design and make changes to the project, an upgrade over the first iteration. A single design change updates the entire project and is checked against local building codes.
Early customers are already using the second version, and the company says it will become publicly available this week. Blueprints AI is already working on a third version that will add structural analysis and electrical panel design. That road map points toward more engineering-heavy tasks, but the co-founders say the technology does not replace licensed architects. Licensed professionals still review the documents and affix their seal before submitting them for permits. The judgment stays human, they say.
Training on real approved drawings
Dram and Cao met at an AI conference several years ago and combined their skills to build the company. Cao, a data scientist from Hong Kong, handles sales and go-to-market strategy as chief commercial officer. The pair trained their models using eight years of approved drawing sets from Dram's design and construction firm, which is still in business.
That training approach matters because architectural drawings are not generic text. They encode jurisdiction-specific conventions, symbols, dimensions and code interpretations. Approved sets offer examples of documents that passed review, though AI systems must still be checked for errors and local variations. The company's claim is that its models can generate and revise permit-ready documents, not that they eliminate professional review.
The 80-20 problem in architecture
Dram said architects spend about 80% of their time on drafting and only 20% on design. He wants to flip that to 20-80. That complaint is familiar across the architecture, engineering and construction industry, where repetitive documentation, coordination and rework consume large parts of the workday. Supporters of AI drafting tools argue that automation can free architects for design, client communication, site analysis and complex problem-solving.
Skeptics note that automated output can create new review burdens if errors are hard to trace, if drawings do not match local code, or if changes ripple unpredictably across disciplines. Blueprints AI says its second generation addresses coordination by updating the entire project when a design changes and by checking the work against local building codes. The company is also positioning the product as a drafting accelerator rather than an autonomous architect.
Permit-ready is a high bar. Building codes vary by city, county, state and country. They are updated periodically, permit reviewers can interpret requirements differently, and projects involve structural, mechanical, electrical, plumbing, fire, accessibility, energy and zoning rules. A system that checks local codes must maintain current code data and explain assumptions. The company's approach of starting from approved drawing sets may help with pattern recognition, but it does not guarantee approval. The final seal and professional judgment remain with licensed architects.
Customers and pricing
Blueprints AI is targeting two groups with its new software. Professional architecture, engineering and design firms make up one group. Developers and real estate owners make up another. The first group needs throughput and coordination across many projects. The second may need feasibility studies, preliminary layouts or faster iteration before hiring a full design team.
The startup offers its software as a subscription and may add a one-time flat-fee option for customers who want it for a single project. First-generation monthly pricing runs from $3,200 to $8,500 depending on the plan, with custom enterprise pricing available. That places the product at a business-to-business price point rather than a consumer design app. It suggests the company is targeting firms that already spend heavily on drafting labor and software.
For developers, faster blueprint generation could shorten due diligence and preconstruction. For architecture firms, it could reduce overtime and allow teams to bid on more work. Adoption will depend on trust, liability, data security, integration with existing CAD and BIM workflows, and whether output is accepted by local permitting authorities. The company says early customers are already using the second version, which will become publicly available this week.
AI in construction documents
Construction and design have been slower to automate than software, media or customer service because the work is physical, regulated and liability-sensitive. Generative AI has spread quickly in concept design and visualization, but permit documentation is more demanding. Errors can be costly, delay projects or create safety risks. That is why Blueprints AI's insistence on human review is significant. The product is positioned as a drafting accelerator, not an autonomous architect.
It joins a broader wave of construction technology trying to use AI for estimating, scheduling, clash detection, code checking and document review. The market is large. Buildings require drawings for new construction, renovations, additions, tenant improvements and infrastructure. Architects and engineers spend significant time producing and revising documents. If AI can reliably reduce that time, the economic incentive is strong.
But the regulatory environment is fragmented, and liability remains with licensed professionals and firms. Startups in this space must prove accuracy, auditability and code coverage. They also need to avoid overpromising permit-ready output when final approval rests with local authorities. Blueprints AI's thesis is that the repetitive portion of drafting can be automated while the professional portion remains human. The company says this will make better spaces because architects will have more time to design. The second-generation launch, pricing model and third-version road map will be tests of whether that thesis holds. For now, the startup is moving from an old student idea to a commercial product at a moment when generative AI has made document generation dramatically cheaper and faster.
Source:TechCrunch News