Founder knowledge engine
Arif KhanStart here
Pick your path.
This site is about one idea: building companies where humans and AI agents work together as a real team. Not AI as a tool. Not automation. A new kind of company.
There are three ways in, depending on where you are. Pick the one that fits and I'll give you a curated reading order — no filler, just the posts that matter.
I'm curious about AI agents
Start with the big picture — what it means to build a company where AI agents have real jobs, then see the team and how it actually works.
I'm building a company where humans and AI agents have real jobs
The foundational essay. Start here to understand the core thesis: AI agents as real team members, not tools.
Meet my AI team: how I'm trying to build a company with AI agents as a non-technical founder
Meet the actual AI agents on the team — who they are, what they do, and how they work alongside humans.
What changes when AI agents stop being demos and start becoming coworkers
What shifts in how you think about work when agents move from experiments to real colleagues.
I want to build with AI agents
The practical path. What agents should own, how to design review loops, and what breaks first when agents enter a real company stack.
What AI agents should actually own inside a company
Where to draw the line between human and agent ownership. The delegation framework.
Building with AI agents means designing review, not just speed
Speed is easy. Quality is hard. How to design the review architecture that keeps agent work reliable.
What breaks first when agents enter a company stack
The failure modes nobody warns you about. What actually goes wrong first.
AI systems should survive contact with real operations
Making AI systems that hold up in production — not just demos, but real operational reliability.
I want to follow the journey
Subscribe and follow along as I build in public. New posts weekly on what's working, what's breaking, and what I'm learning.
Content as infrastructure, not promotion
Why I treat writing as infrastructure, not marketing. The philosophy behind building in public.
Masaya is a proof point, not the whole story
One venture as proof of concept — and why the real story is bigger than any single company.
Enjoyed this?
Weekly notes on building companies with AI agents — what's working, what's not, and what I'm learning along the way.
Join 50+ founders
Latest posts
Darwin Part 3: How Part 1's Scoring + Part 2's Discovery Became a Compounding Loop
If you're new, this recaps Parts 1 and 2. If you're continuing, this is the payoff: how scoring + discovery connect with memory and research so corrections become permanent upgrades.
The Memory Architecture: How Corrections Compound
Without a memory architecture, every AI agent correction evaporates at session end. Same mistake, next week. Borges closes the loop — a Monday correction becomes a permanent skill improvement by Wednesday.
How Hawking Does Research That Doesn't Suck
A single-pass web search produces a confident-sounding summary with six gaps and three outdated facts. Hawking runs 3-6 progressive rounds until coverage hits 80%, and it's not allowed to stop early.