One founding engineer at Utopia Studio built Mentix, a clinical platform for surgical mentoring, in 3 months. Mentix began with Dr. Amyn Haji, who trains surgeons in advanced endoscopy at King’s College Hospital. He worked with the team to write the product Requirements. Software Factory turned them into Blueprints and Work Orders. A working prototype was ready in 3 weeks. "When the people who hold the knowledge help write the requirements, and our stack goes in with them, the work order knows what matters and why." James Cannan, founding engineer at Utopia Studio Mentix TV can broadcast a live procedure to a room of trainees. Live sessions were running by July, including a masterclass at King’s.

Legacy applications carry decades of business rules, edge cases and operational decisions. In the recent webinar “Inside the modernization factory: From discovery to delivery with AI agents,” our co-founder and CTO @sinasojoodi joined Mara Puisite, Executive Director, Technology Consulting at @EY_US, to explain how teams preserve that context throughout modernization. The six-stage process carries legacy business logic from discovery into a validated modern system.

Happening tomorrow: @yucjonathan demos Software Factory agents working through a bug and turning customer feedback into an implemented feature, live. September 16 · 9 am PT / noon ET Bring your questions. Register:

Two workflows Jonathan Yu will demo live next week: → Automatically resolving a bug → Turning customer feedback into an implemented feature We’ll get into how Skills compound productivity, followed by Q&A. September 16 · 9 AM PT / 12 PM ET Bring your questions for the live Q&A. Register below.

Every large IT transformation program starts with a seemingly defensible choice. You pick a firm nobody can criticize you for picking, to help you transform. That made sense when the key question was whether anyone could build the thing at all. But AI changes this. The biggest study ever run on large IT programs, by McKinsey and Oxford, across more than 5,400 projects above $15M found they come in 45% over budget and deliver 56% less value than planned. The time overruns are just as bad as the cost overruns and can add years to meet objectives. What solves this is a system that, in part, can help you document your intention with clarity up front. Then the execution and verification can take advantage of AI to deliver what you want on time, on budget and on scope. That's how every engagement starts with 8090 Software Factory. Here is how it works:

Red Oak Development's CRM sat untouched for years. When the team came back to it, much of the knowledge of how it worked had gone cold. Three months on Software Factory, it is back in active development. The full story:

Bissell is a 150 year old American family owned business based in Grand Rapids, Michigan. It’s a multi billion dollar manufacturing business who has revenue streams around the world and has to compete against tough competition from China everywhere so productivity, speed, and eliminating waste are critical to their competitiveness. 8090 worked with Bissell to identify a roadmap of potential projects to improve productivity and revenues or reduce costs. Our first program with them has added a lot of learning to our playbook in manufacturing while delivering measurable time and cost savings for them. Hear more from Bissell’s CFO, @matthew_kruer here:

Melville Bissell patented a carpet sweeper in 1876. In 1889 his wife Anna took over and became America's first woman CEO, building it into the largest company of its kind in the world and setting its early standards for trademarks and patents. BISSELL is still family-owned 150 years later. Every product is built from parts, and every part needs an approved name before engineering can start. That approval ran on Excel forms, applied by hand against rules that lived in the heads of people who have been there 40 and 50 years. We built the system that runs it now. 7,000+ parts submitted, 81.4% approved in seconds, and reviewers spend their time on the ones that need a decision. The full story:

On Control Planes… Four companies shipped an enterprise AI control plane in the last two weeks. They all do one thing well which is govern which model answers a request and what it costs. That’s a real problem and I’m glad it’s getting solved. But what none of them capture is why the software was built that way in the first place, or which requirement a given change was meant to satisfy. Now years later, when an auditor or regulator or senior exec asks for exactly that record, the engineer who made the decision will be gone and the model that wrote the code will have been retired. Now what?? We live this at 8090. At CMS, for example, we extracted 100,000+ business rules from ~18 million lines of Assembly + COBOL because nobody recorded the intent when it was originally written. Recovering it decades later is expensive and the cost was avoidable. My best guess right now is that control planes that are only ever a model gateway, no matter how feature rich, will commoditize. The durable asset is capturing the record of intent, and we think the only way to get it is to put that workflow at the center of a factory that oversees how software gets built in the first place. That’s the bet inside 8090’s Software Factory. Learn more here:

We all know an employee who can do everything. @melbourneandrew, Head of Engineering for Software Factory on how an agent harness can 10x the efficiency of your best employee. 🚀

Build-vs-Buy Math is Now Squarely in Build For the entirety of the SaaS wave, it was always cheaper and faster to buy software vs build what you needed. But the buying cycle continues to get more complicated. Gartner says the buying group for a complex enterprise software purchase is 6-10 people. 77% of buyers describe their most recent purchase as very complex or difficult.  That process exists for well known reasons: someone runs the security review, another negotiates the terms and another signs off on the risk.  But because of AI, the “build” side of that comparison has now moved materially. When a “buy” evaluation still takes two or three quarters just to clear procurement but the workflow you want can now be specified, built, tested and running in production inside that same window, the oldest argument for buying, that it was the faster path is, no longer true. We built Software Factory to help large enterprises take advantage of AI’s deflationary economics and make a build vs buy decision much more competitive than it has been historically. 

How:

The insurance industry has priced the AI risk.  Carriers went to state regulators this year asking to exclude AI-related damages from ordinary general liability policies. 

Regulators approved more than 80% of those requests, and the standard forms behind roughly 82% of American property and casualty coverage now carry a generative AI exclusion that gets attached at renewal.  Underwriters are telling you they can't price a loss they can't inspect or audit . This is the same problem all large enterprises have with examiners, regulators or auditors when they ask “Show me what happened and demonstrate that your controls actually worked.” Imagine a bank builds an AI agent. The agent makes a decision that causes a $20M loss. The bank asks the insurer to cover it. The bank’s insurer asks: What exactly happened? Which model was running? What information did it receive? What tools did it invoke? What actions did it take? What rules constrained it? Was a human involved? Can you reproduce the sequence? If the answer is essentially “we don’t know - the model made the decision”, the bank has a nightmare and the insurer will balk. It can’t determine causality, negligence, controls, or even whether the same thing could happen tomorrow. But suppose the software has an immutable audit trail: Prompt → context → model → reasoning/action path → tool calls → data accessed → permissions → output → human approvals → final action Now the loss is inspectable. An insurer can underwrite it much more like conventional operational risk. Software that keeps a traceable record of what it did and why is how a regulated business answers these questions. This is the part we build:

50 to 80% of a software system's lifetime cost arrives after launch. At launch, a system integrator's delivery team rolls off to the next engagement, so the people who made design decisions are gone before the expensive years begin, and the support begins. Ask who takes the call three years in, when a regulation changes or the workflow the system was built around no longer exists. The engagement model was designed to end exactly when most of the cost begins. 8090 stays accountable for the code in production after go-live and keeps it current as the business changes. 

Learn more:

1 week out from our @EYnews x 8090 Modernization webinar. It will cover: ---> Discovery and Portfolio Analysis ---> Large-scale delivery ---> Practical methods for reverse engineering legacy ---> Where AI agents fit ---> How people approve/audit every step One hour with live Q&A. Reserve your spot:

Big release week for Software Factory: Major Features Skills Module Create and edit agent skills in a dedicated module, collaborate with teammates on them, and publish them to an organization-wide Skills Library for reuse across projects. Durable Agents Agents keep running in the cloud when you close your machine, so long tasks finish without you staying connected. Knowledge Base MCP Tools Expose your project's Knowledge Base over MCP so external agents and tools can read and search it.

Retiring spreadsheets in favor of software… 8090 built the system that now runs part and model numbering inside BISSELL’s product development organization. The rules that a handful of expert reviewers once enforced by hand are now written into software, requests that follow them are approved in seconds. Reviewers only give their attention to the requests that need it. Also, because the system is built with the help of our Software Factory, it is well documented, auditable and can change on a dime by simply editing the rules. The system now runs at about half the annual cost of the process it replaced.

An engineer sends twenty part names for approval and waits on a reviewer's calendar, even for the sixteen a computer could have approved on sight. BISSELL retired that process. 8090 wrote the reviewers' rules into software, and 81.4% of parts now approve in seconds at half the annual cost. The full story: