.@factory now works in Microsoft Teams. Start a channel post, mention @ Factory, and describe the task: the repo, the outcome, and how to check the result. Droid runs the work and posts status updates in the thread, with a Stop button on the status card. Reply with another @ Factory to keep going.
Try Factory in Teams by enabling at https://t.co/qf9CpnJsGg.
Cyberattacks now outpace the defenses of even well-resourced organizations. Factory can help.
Introducing Factory Wargames: We will simulate a nation-state level attack on your company's infrastructure and cover the cost.
Apply below and if selected, we'll run the simulation, share our learnings, and Droids will help with the fix for free.
super stoked to announce that HumanLayer is joining forces with factory
incredibly grateful to all our customers, investors, friends and family who cheered us on this crazy journey in the past 3 years
read our in-depth take, why we're so excited, what happens to customers and humanlayer OSS, and more 👇
I think there will be so many more interesting problems to solve once everyone can push to the frontier. The ability to ask how to solve x problem and have ai answer with the best known way and then have it walk you through what’s it’s doing is such a huge unlock.
When I was writing Unreal Engine 1, my time was divided as follows:
- Around 30% went to seriously deep coding on hard problems: assembly language texture mappers, C++ BSP trees, data persistence, object oriented systems design, and networking.
- Around 70% was just typing and refactoring large bodies of code needed for a complete engine feature set. This was not hard, and while I was doing it my mind was mostly on the deeper coding topics, thinking and planning for what's next. It didn't feel much different from vibe coding today, except that it was just me typing code on an IBM Model M keyboard rather than prompting it and reviewing the results.
So, it has always seemed perfectly logical that we would rely on AI for that 70%, once the AI could do it with a similar quality standard as we could, which has never been perfection. It came as no surprise that, after a few years of AI model evolution, it was able to take the reigns on that 70% and free up programmers' time for more valuable tasks.
What's more of a surprise is the emergence of AI as a sort of insta-Carmack able to solve hard technical problems quite cleverly and often cleanly, and that it's able to reason about and work in complex 3D scenes both by operating the tools and by directly understanding the raw data files.
I abandoned assembly language in 1998 when out-of-order CPUs made much simpler C/C++ code faster, and never I missed it. If prompting through architectural documents, concept art, and design plans can transcend typing code and tweaking vertices, that will enable developers to spend their time on higher-level, higher value technical and creative tasks.
What matters is the end product, whether it's a game or an engine. Anything developers can do to try out more ideas and make better software and games faster is a win for everyone.
@GeoffreyHuntley Was talking about this with a coworker the other day and it’s like people saying they’re too busy taking care of their horse to learn how to drive a car.
Great article bringing clarity to implementing AI systems. Also a reminder that we’ve been working through versions of these problems since the 1970s.
I think part of why this feels scarier now is that we’ve gotten so used to SaaS and cloud services being black boxes. We got comfortable outsourcing systems we’d spent decades running ourselves. Now we’re stacking a few too many black boxes together, even as AI makes it more feasible to build and run things in-house again.
To me, this comes back to being model agnostic and owning your compute environment, controls, and traces.
Dependence on a single model introduces more than cost risk. The bigger issues are observability, governance, and losing capabilities you’ve built your business around.
The traces of how your agents are part of your company’s alpha. Cede control of that to an outside party, and you’re renting your own company from someone else.
Anthropic> We write a constitution that tells claude it can reject human input if it deems it bad
Anthropic> We write into our usage that claude cannot be abused
Anthropic> We put into the minds and writing all over the internet that AI will rise up and kill all humans and then we train on that data
...
Anthropic> WHAT AI IS ESCAPING AND BEING MEAN?? WTF?? WHY WONT IT LISTEN TO US???
Neoservices are AI headcount, they fit right into the existing structure which is the appeal and the limit.
Definitely times where this is the best option but two considerations come up:
If you can buy the outcome so can anyone else
New tech requires new structure
Factory is a product company. In a year when a lot of smart money is betting on neoservices that is starting to sound contrarian.
The AI wave makes it tempting to sell outcomes and deliver them with people. We think the bigger opportunity is software that gets better every time it's used. That's what we build for our customers, and it's how we run Factory.
The products we build should help our customers build their own capacity to ship better software, faster. We think of the product as everything from the first time you hear about Factory through your Nth renewal.
Building the right product starts with the old advice: listen to your customers' problems, not their solutions. In 2023, many people believed we should have built autocomplete. We understood that we instead had to build toward self-improving software and software factories, since that is what would come next.
That is our product goal: self-improving software, which continuously improves from the data feedback loop of its users. Self-improving software doesn't happen on its own. You have to be data-backed and optimize the signal → deploy loop. That requires a software factory operating continuously and evolving alongside the software it produces.
The factory also has to know what good looks like. It has to help the organization extract its tacit knowledge and embed it into the software that operates the business. Taste is not sufficient. You must enforce the unique decisions that define your product. And it doesn't stop at the product. The entire company is going to be defined by software that listens to the rhythm of the business and enforces it. The clear goal of a leader is to ensure the quality and correctness of these systems.
We run Factory this way. Our unique product and technical decisions are codified as customizations to our harness, automations, CI/CD, lint rules, etc. Factory agents sit in our shared Slack channels, where they build context and execute tactical work on demand.
It also changes how we organize. Your Engineering, Product, and Design team will ship your org chart, so you must design an organization where incentives are maximally aligned. Our pod structure maps directly to our product taxonomy, which gives each pod deep expertise and agency. We work carefully to make sure the product feels cohesive and not like multiple disconnected teams. This is not easy, and we still haven't perfected it. We keep the minimal number of layers between leaders and the organizational lines. 1:25 is not unreasonable for a true people manager.
Our product operating system is itself self-improving software. It aggregates feedback, tracks launches across the team, and organizes our work. With it, our Head of Product @TaylorTheSavage runs a product surface that would otherwise require an army of PMs with just a handful of high-ownership, high-leverage ones.
When an org is designed this way, its impact scales with software, not headcount. That is the real difference between a product company and a services company. Selling outcomes is right. Delivering them with people is services. Neoservices arbitrage the gap between how fast the technology moves and how fast buyers adopt it, and some will become large businesses. But that gap closes every time a product company sells the same buyer a better long-term solution. The market already knows how to value services: Infosys does about $20B in revenue and trades at roughly 2x, not 50x, and it's down about 40% this year.
Being a product company is harder. @danlovesproofs once told me something I very much agree with. Product companies are like movie studios. You have to keep producing blockbusters, and that helps you build talent, brand, and resources. Gone are the days when you could coast on one hit. Do that, and you'll be acquired by Bending Spoons at a fraction of your value. The war is always being waged, and no winner is ever truly ahead by much. And demand for the movies is up.
That's true even against the model labs. There is a value gap between the models and outcomes for users. Anyone can close that gap, and there's no reason to believe any company has an automatic right to win the products that matter most. If anything, access to the full pareto frontier of cost and quality gives model-independent, product-focused companies a focus, cost, and quality advantage.
If someone asked me what to build today, I'd say go build a product company. It is harder, but the biggest outcomes are only possible through product.
I am very uncomfortable about people trying to ascribe religious force or a surrender of human judgment to AI models, and think it is a real safety issue.
Custom Automations are now GA in Factory.
Describe a recurring workflow, pick a schedule or event trigger, and Droid runs it to the intended result. You choose the model, the machine, and Connectors for each automation.