Here are some real examples from our projects in 2025 at SIROC (for context: we are a 18 people venture studio; 140+ projects completed):
* A task estimated at 4 hours → solved with one well specified prompt
* A 20 hour engineering effort → executed in about 3 hours
* A 3 month project → delivered in 1 month
These are clearly best case scenarios. They are not the norm, yet. But they demonstrate what is possible.
We have also seen what happens when things go wrong. Companies, including startups, come to us with broken systems and spaghetti code and architecture caused by weak prompts, unclear requirements, and no verification.
It is important to understand that the efficiency gains we are seeing do not come from the tools alone. They come from a specific combination:
1) Engineers who have spent 20 years building everything from robotics to enterprise-scale technology. You cannot give a perfect instruction to an AI if you do not know what perfect looks like in a production environment.
2) A technical prompt should not be treated as a quick input or question. It is a detailed specification that requires experience and deliberate thinking.
3) Knowing the right combination of tools, workflows, and validation processes.
That said, some (many?) members of our team are dinosaurs in the software engineering world. They bring a ton of experience but are used to tools from 15 years ago and don't like change. We really had to push AI adoption (mostly Cursor and Claude Code) on them. It’s still an ongoing process, and probably will be for a while.
I was thinking last night about whether this is even a realistic moat or not.
Right now, Claude is getting trained by hundreds of thousands of programmers showing it how to ask the right architecture + PM questions.
They're just patterns, like anything else in our industry, and most of them are pretty standard patterns.
Like when I think back on 20 years of software architecture and BA work, I've done the same thing over and over. I must have implemented 4 PO systems, 3 different custom chat systems, SMS systems for reminders, monthly summary emails, etc.
We are a small senior-only team of former startup founders and engineers who act as the technical engine for startups and scale-ups. We skip the junior developers and project managers to focus on high-speed shipping only.
What we do:
* For Startups: We act as fractional co-founders, turning napkin ideas into investor-ready products. We’ve helped founders take ideas to $20k MRR in just a few months
* For Scale-ups: We audit and rebuild tech stacks to handle 100x growth.
* Our Background: Our team originated at Stanford. Our track record includes building core infrastructure for high-growth tech startups and global platforms. We’ve delivered 140+ projects over the last 20 years.
Our guarantee: We deliver a working product in under 90 days, or you don't pay.
If you’re a founder who needs a senior strike team to take full ownership of your roadmap, email me at hello@siroc.com
It’s probably just a coincidence, but there seem to have been significantly more aviation incidents in the past two years than in the previous 40 years of my lifetime.
I just realized that Google Docs now has tabs, allowing multiple pages within a single document. Very similar to how we use Notion for writing down documentation, SOPs and general company information.
Has anyone tried this feature yet? Do you think it's enough to replace Notion for wiki-style documentation?
reply