AI Native Company

2 people. 250k+ lines of code. 3 weeks.

Most customers (and a couple of investors) flat out don't believe a 2-person team shipped OXYGEN this fast.

I'm not even saying it's good. But it's what going AI-native actually looks like.

The term gets thrown around a lot. Here's what it means inside our company, end to end.

1) Development

We run 4-6 coding agents in parallel. Mostly Claude Code and Codex.

Building the first 80% is the fun part. The last 10% is where it gets brutal, and that's where the systems earn their keep.

We burn ~$1.5k/month on tokens. Coding plus code review agents.

2) The product itself is built for agents

This is the part most people skip. If you're AI-native, your product has to be too.

We built OXYGEN CLI and MCP-first, so agents can actually operate it.

The ironic part: OXYGEN isn't powered by AI in its architecture. We don't run our own agent runtime yet. It's powered by agents like Claude Code and Codex sitting on top of it.

Built for agents. Built by agents.

3) Quality runs through a pipeline

Early on it was messy. Probably normal for every startup.

Now every production merge runs through:

→ deterministic tests in the PR → 3 review agents in the background: Greptile, DeepSource, Cubic

Bugs in prod dropped hard.

4) GTM runs the exact same way

Our content engine and our outbound engine are both powered by OXYGEN, which is itself driven by Claude Code.

Newsletters, content, outbound. Same agents, same token budget.

5) Tool selection has one rule

We only adopt tools we can drive via CLI or MCP.

Newsletter platform, internal ops, all of it. If an agent can't operate it, it doesn't make the stack.

None of this is the "right" way to build a company. But for a 2-person team, it's the only way the math works.

How many agents are you running in parallel right now?