This one hit differently.

Jesse Light has been a structural engineer for over two decades. He started as a mechanical engineer, worked at Orbital Sciences, and then spent years figuring out why structural engineering software — built by different companies, for different purposes — never talks to each other. And why all those hand-offs between programs were where errors lived.

Cole Fowler came up differently. SML was his first job out of college. He learned to code in MATLAB at ASU, joined a firm that actually let him fix the things that annoyed him, and ended up building automation tools that changed how SML competes.

Together, they represent something rare in the AEC industry: a structural firm that treats software as a strategic advantage, not just a toolbox.

Thanks for reading Genia! Subscribe for free to receive new posts and support my work.

What we talked about:

We met at an NCSCA event where Jesse was presenting SML’s automation systems to his peers. The conversation that followed led to our collaboration — and eventually to this episode.

Here are a few things that stuck with me:

On what “automation” actually means for a structural firm: Jesse described watching data flow from one software to another — RISA 3D to MathCAD to Excel and back — and realizing that every hand-off was a place where a tired brain could drop a decimal. His solution was elegant: build a pipeline so the engineer’s job is engineering judgment, not data entry. As Cole put it: “I don’t want to be checking numbers. I want to be solving engineering problems.”

On what happened when SML started working with Genia: The first ADU project we did together took time. We built the standard carefully. The second was faster. The third was faster still. Jesse described going from 20 hours → 10 hours → 5 hours across three iterations — not between projects over a year, but within the same engagement. The AI system locked in a methodology; the engineers refined it in real time.

On how a licensed SE maintains engineering control with AI-generated designs: Cole’s answer was reassuring in its clarity. The building code dictates the equations. Genia’s system isn’t inventing new structural logic — it’s applying the same code equations, consistently, every time, in a format that makes checking fast. Cole compared it to when FEA software first came out: experienced engineers still ran hand calcs alongside it to validate. Same discipline applies here. “Your AI tool is far faster [than an EIT], but I would still have to vet all that information.”

On FTAO design and real dollar savings: This was one of the most concrete moments in the conversation. Force Transfer Around Opening (FTAO) lateral design lets engineers use the full wall assembly — openings and all — as a shear wall, rather than designing around them with dozens of individual hold-downs. Removing 12 hold-downs from an ADU isn’t abstract. Each one costs hundreds of dollars in hardware, labor, and inspection. In some cases, the engineering fee pays for itself just in hold-down savings.

On AI and the careers of young engineers: Cole introduced a phrase I hadn’t heard before: cognitive surrender — the risk that engineers stop trying to interpret results and just let the AI do the thinking. His view: as long as you’re engaging with the output, building intuition, understanding what you’re seeing, using AI to iterate faster is just another step in the evolution of the profession. “It’s really no different with each step in technology. It’s just one more tool in our tool bag.”

Thanks for reading Genia! This post is public so feel free to share it.

Listen to the full episode: Spotify | YouTube

Structural Stories is Genia’s podcast featuring conversations with structural engineers, builders, and construction leaders on how AI is reshaping the way we design buildings.

→ If you build homes, design structures, or run a structural firm and want to explore what working with Genia looks like, reach out here.

For our first episode, I sat down with Dr. Murat Melek, Senior Director of AI at Suffolk Construction. Murat is one of the most thoughtful people I’ve met at the intersection of structural engineering and artificial intelligence — someone who started his career doing hands-on structural design at Arup and Walter P Moore, then gradually moved toward visual programming, Python, and eventually full-on AI strategy at one of the country’s largest GCs.

We’ve been collaborating for almost two years now, and this conversation gave us a chance to reflect on what we’ve built together, where the industry is headed, and what young engineers entering the field today should make of all this.

Thanks for following Genia! This post is public so feel free to share it.

A few things that stood out to me from our conversation:

On why automation makes sense for structural engineering Murat put it plainly: the structural workflow involves repeating the same process over and over. Building models, running loads, generating schedules — it consumes time without producing much learning. The question isn’t whether to automate, it’s where. His answer: framing and preliminary design are prime candidates because the guardrails are well-understood and the failure modes aren’t catastrophic. The critical judgment calls — shear checks, deflection, coordination — still need an engineer in the loop.

On how Suffolk actually uses Genia’s API Rather than putting structural engineering software in front of architects or pre-con staff who don’t want to use it, Suffolk’s team preps and transforms building model data into a schema Genia can process, then pipes the results back into their workflow. The use case that kicked it off: a series of one-story steel buildings across multiple locations with varying geometries. Being able to change a parameter, hit send, and get a structural response back in seconds is genuinely valuable when an architect is finalizing a layout under deadline.

On trust and accuracy This is where things get nuanced. Murat made a point I think about a lot: engineers today spend so much time building the model that they have almost no time left to interrogate the results. AI should flip that ratio. You want high-level benchmarking and element-level detail available simultaneously — not as a replacement for engineering judgment, but as a way to make that judgment faster and better-informed.

On the shift to outcome-based services We spent some time on a question that I think will define the next decade of AEC: does the client care how many hours went into a structural design, or do they care that it’s accurate, well-coordinated, cost-efficient, and doesn’t generate RFIs on site? Murat’s view: the technology is now here to make outcome-based billing inevitable. Licensure and stamping aren’t going away — accountability still matters — but the billable-hour model for repetitive design work is on borrowed time.

On the workforce question This is the one I keep coming back to. If AI is handling the work that used to train junior engineers, how does the next generation develop intuition? Murat’s take is that this is ultimately a user experience problem: we need to design systems that give young engineers feedback on the consequences of design decisions, not just output that makes decisions invisible. Domain expertise, planning, and the ability to translate engineering intent into language AI can act on — those are the skills that will matter most.

Thanks for reading Genia! Subscribe for free to receive new posts and support my work.

You can also watch or listen to the full episode on YouTube. If you have thoughts, questions for future guests, or someone you think we should have on — I’d love to hear from you.

— Zhihao

In this 17-minute walkthrough, I take a single-family home project with a rafter roof system through every step of Genia’s workflow: uploading the CAD file, parsing the floor plans, modeling the architecture, generating the structural framing, and exporting a complete permit-ready package.

No cuts, no speed-ups. Real project, real time.

Thanks for reading Genia! Subscribe for free to receive new posts and support my work.

What you’ll see in the video

The project is a two-story single-family home. Here’s what the walkthrough covers:

* CAD upload and validation — how Genia checks your file before parsing, including segmentation, alignment, and wall checks

* Floor plan parsing — automatic detection of Floor 1, Floor 2, and the Top Roof from a single drawing file

* Architectural modeling — walls, openings, windows, doors, attic settings — all editable in 2D and viewable in 3D

* Rafter roof framing layout — the rafter system laid out in plan view, with ridge, rafters, purlins, and bracing visible in the 3D section view

* AI structural generation — Genia runs calculations in the background and returns design options in under 20 minutes

* Structural design review — toggling through beams, joists, posts, rafters, shear walls, and foundations in the 2D layout

* Calculation report — the full PDF output, including design basis, loading maps, vertical and lateral load design, and critical member checks for rafters, purlins, bracing, beams, posts, shear walls, and strip footings

The calculation report alone is 460+ pages — design basis, ASCE environmental loads, vertical load design, lateral load design, and critical member checks for every structural element. All generated automatically.

Thanks for reading Genia! This post is public so feel free to share it.

Why rafter roofs specifically?

Rafter framing is one of the most common roof systems in residential construction — and one that requires careful attention to ridge loading, rafter span, and lateral bracing. It’s a good test of what an AI design agent actually needs to get right.

This walkthrough shows Genia handling it end to end.

Questions about the workflow, the calculation outputs, or how Genia handles your project type? Reply to this email or leave a comment below — I read every one.

It’s not the interesting parts. It’s the load takeoffs. The parameter inputs. The layout iterations. The manually drafted connection details. The calculation sheets that nobody outside your firm will ever actually read — but that need to be 212 pages long and code-compliant regardless.

We built Genia to handle that part of the job. And today, I wanted to show you exactly what that looks like in practice.

Thanks for reading Genia! Subscribe for free to receive new posts and support my work.

What’s in the video

This is a real project walkthrough — not a polished demo with a cleaned-up model. I’m uploading an actual Revit file and walking through every step the way you would on a live job.

Here’s the sequence:

Step 1 — Upload & Project Setup Uploading a 7.6MB Revit .rvt file directly into Genia. The platform accepts both CAD (DWG) and BIM (Revit) formats. From there, project name, address, and a quick file validation check.

Step 2 — Building Code & Site Parameters This is where Genia pulls its weight early. Selecting IBC 2024, site class, exposure category, risk category — then the platform automatically fetches seismic parameters (S1, Ss, Sds) and base wind speed for the project address via ASCE API integration. Gravity loads, soil parameters, deflection limits, and approved materials are all configurable here.

One choice I want to highlight: Optimized vs. Conservative shear wall design. Option 1 minimizes hold-down hardware using advanced analysis. Option 2 takes a conservative/robust approach with simpler installation. This is the kind of design decision engineers used to make after hours of iterating layouts. You’re making it at the start, before any drawing is produced.

Step 3 — Architectural Modeling The AI parses the Revit model and produces an editable floor plan and roof plan. Walls, doors, windows, openings, columns — all recognized and rendered as a structural model. You can review and correct any parsing before moving forward.

Step 4 — Roof Framing Layout Regular truss framing layout, generated and displayed on the floor plan canvas. Editable. You can flip direction, switch between truss types, or add beams manually.

Step 5 — AI Generates Structural Design Options This is the part that used to take days. Genia explores hundreds of layout options, runs physics-validated structural calculations on each, filters out anything non-compliant with the building code, and presents you with the top options to review.

In the video, I show Option 2 — a 3D structural model with every layer visible: walls, shear walls, beams, joists, regular trusses, girder trusses, and the foundation system. You can toggle each layer, switch between 2D and 3D, and review load analysis before exporting.

Step 6 — Export One click. The platform packages the full structural drawing set as a CAD file and a calculation report as a PDF.

The outputs from this project:

* Permit-ready structural drawings, opened in AutoCAD 2026

* A 212-page structural calculation report — covering design basis, vertical load design, lateral load design, critical member design examples, and appendices — all powered by Genia, ready for engineer review and stamping

Why Revit support matters

Most of our users have been uploading DWG files. Revit support opens the door for firms and developers whose architects are delivering BIM models — which is increasingly the standard on new residential projects, especially in California.

If your upstream workflow is already in Revit, you no longer need to export to DWG first. Upload the .rvt directly and start your structural design from there.

Try it yourself

The full workflow in this video — from file upload to exported drawings — takes under 20 minutes of active time (the AI generation step runs in the background, so you can step away).

Start a free project → https://genia.design

New accounts include 100 free credits, enough to run a complete single-family project. No credit card required.

If you’re working at scale — multiple projects per month, team review workflows, custom material libraries — our Team and Enterprise plans are built for that.

Questions?

Drop them in the comments. I read every one.

If you have a specific project type you’d like to see walked through — multi-family, ADU, retrofit, wood vs. steel — let me know. We’ll make it.

— Zhihao CEO & Co-founder, Genia

Genia is a Structural AI Agent used by 200+ structural engineering firms. We generate physics-validated structural designs from architectural drawings, with permit-ready CAD outputs and full calculation sheets. Learn more → genia.design

Thanks for reading Genia! This post is public so feel free to share it.

* Loading and configuring the structural model

* Defining truss geometry and parameters

* Setting up loads and boundary conditions

* Running the AI-assisted structural layout

* Interpreting member forces, deflections, and code compliance

If you work in structural engineering, architecture, or anywhere in the AEC space and you're wondering what AI-augmented workflows look like today — this is a concrete example.More walkthroughs coming. Hit reply if there's a project type or workflow you'd want to see covered next.

The industry standard for residential structural design is 2–3 weeks. But “standard” doesn’t mean acceptable when your permit is unfiled, your subcontractors are getting booked on other jobs, and your client is losing patience.

The problem isn’t your engineer. It’s the workflow.

Traditional structural engineering is bottlenecked at every step: manual code research, hand calculations, iterative drawing revisions. A talented engineer working the old way simply can’t move faster than the process allows.

That’s exactly the problem Genia was built to solve.

How Genia’s AI-Augmented Engineers Work

We don’t replace structural engineers — we make them dramatically faster and more accurate by pairing them with AI.

Here’s what the process looks like:

Day 0 — You submit your project. Upload your architectural drawings (.dwg or .rvt), project location, and any special structural requirements. Within 4 hours, you’re matched with a licensed structural engineer in your state.

Day 1 — AI does the heavy lifting. Genia’s AI model analyzes your drawings, runs structural analysis, and generates hundreds of optimized design options in minutes — work that would take a human engineer days. It identifies the structural configuration that is both code-compliant and material-efficient.

Days 2–5 — A licensed PE or SE reviews, refines, and stamps. Your engineer reviews the AI-generated designs, applies their professional judgment, and delivers sealed, permit-ready drawings.

That’s it. Five business days. Guaranteed in the contract.

What the Numbers Look Like

Across 1,200+ projects completed through Genia’s network of 1,300+ structural engineers:

* 10x faster than traditional workflows

* 20% less structural material on average — the AI finds efficiencies a human working under time pressure typically misses

* 40% fewer errors — which translates directly to fewer permit revision cycles and faster approvals

For a custom home builder doing 10–20 projects a year, a 20% material savings across structural packages is a meaningful number. And for a design-build firm whose reputation depends on hitting timelines, a written delivery guarantee changes the conversation with clients entirely.

Who This Is For

Genia’s AI-augmented engineering service is purpose-built for:

* Architects who need reliable, fast structural turnaround to keep projects on schedule and clients happy

* Custom home builders and design-build firms managing concurrent projects where delays compound

* ADU developers who need fast, cost-optimized structural packages at scale

* Production homebuilders rolling out tract or prefab communities where material optimization compounds across hundreds of units

We handle ADUs, single-family homes, duplexes, townhouses, and apartment buildings — with engineers licensed in all 50 states.

A Written Guarantee

Most engineers can’t tell you when your drawings will be ready. We put it in the contract: 5 business days for residential projects, with a refund if we miss.

That’s not a marketing claim. That’s because when AI handles the time-consuming computational work, the schedule becomes predictable.

Submit Your Next Project

If you have a project in the pipeline — or a current project where structural drawings are the bottleneck — submit it at genia.design/ai-engineers and get a quote within 4 hours.

Structural engineering should be the easiest part of your project. Let’s make it that way.

Genia develops Generative Design Copilots that help structural engineers produce permit-ready drawings 10x faster with 40% fewer errors. Learn more at genia.design.