Why? Multi-tenant environments. First, we need to understand a few differences between environments:

• End-user UI
• Agent Runtime Environment
• LLM Server

So

• When you run Claude Code on your local MacBook, the first two are always local. The third is usually the Claude.ai server.
• When you ssh to a virtual private server (VPS) and install Claude Code there, the first two are your remote server. The third is still the Claude.ai server.
• When you run Claude RC on your virtual private server and code from your iPad using the Claude app, the end-user UI is on your iPad, the agent runtime environment is on your VPS, and the server is still Claude.ai.

Most people physically separate their tenancy, such as Claude Code, from their personal vs. work laptops. So in most cases, it's not a big deal.

But when you need multi-tenancy, it becomes super stressful. For example, say you have two different toolkits:

• personal toolkits (personal Notion, personal Sentry, personal Linear)
• workplace toolkits (company Notion, company Sentry, company Linear)

Most MCP auth states or code harnesses don't support profiles, so you can only log in to one.

So therefore... a natural evolution was to have both:

• a personal VPS with all personal toolkits set up
• a workplace VPS with all workspace toolkits set up

to physically isolate tenancies.

Now we've solved the multiple-profile issue, but the client's problems persist. Now let's get back to the environments:

• End-user UI
• Agent Runtime Environment
• LLM Server

All MCP auth or toolkit auth info should always be saved in the Agent Runtime Environment IMHO. However, a surprising number of harnesses tie them to the LLM server (such as Codex Apps or Claude.ai Plugins) or put them in the end-user UI (Claude Desktop or Codex Desktop).

Now the problem is:

• If the auth data is put on the LLM server, you cannot reuse LLM accounts across tenants
• If the auth data is put on the end-user UI, you cannot use the same app to access multi-tenants.

The only way to reliably isolate different auth information is thus:

• You ssh to a virtual private server (VPS) and run Claude Code there. Never use LLM server plugins.

Then

• End-user UI
• Agent Runtime Environment

are both isolated VPS, and

• LLM Server holds no information on the tenancy

This way, you can provide different toolkits, creating multiple dev environments.

This is a story about how I lost $10,000,000 by doing something stupid.

The Beginning

The model they used for Basecamp was to build great software that scratched their own itch (project management,) and charge a monthly recurring amount to give them access (SaaS) assuming others had the same problem. Then, focus on organic growth via product improvement and public writing. Finally, spend less than they make!

When we turned on billing for our beta users, we jumped to 20k MRR in the first month. We started growing at 10% per month and were the new hotness. I got reach outs from all the top VCs and tons of tech luminaries started using the product. We'd made it…or so I thought. We consistently spending 2-3x our monthly revenue and losing money. Not venture capital. Out of my personal bank account, hopes in making much more.

Asana

Then, Asana. With a team a quarter of the size, and a fraction of the money, we had built what I felt was a superior product. Around this time, Dustin invited me for a coffee in San Francisco. He implied--in the nicest possible terms--that they were going to crush us. He walked me through who was backing them, how much cash they had, how they had hired top executives from huge companies, and that it was only a matter of time until they beat us on product and outspend us on marketing.

I laughed! I was on the bootstrapping train. He was drinking Silicon Valley KoolAid. Nice try! I told him let the games begin and we left with a friendly handshake. Flow kept growing quickly, but our customers were demanding.

Asana quickly released clients on all platforms. After all, they had a dev team 5x the size. Suddenly it was a key feature when people compared Asana and Flow side-by-side. Mobile was table stakes. We had to keep up. Almost overnight, our burn doubled. We lost the war, due to inexperience, product myopia, and a lack of capital in a highly capital intensive and competitive space.

Takeaways

1. If you are in a competitive VC-funded space, it's foolish to compete without raising money. Don't bring a knife to a gun fight.
2. The best product doesn't always win, and product is not a longterm competitive advantage.
3. If a tree falls in the forest and nobody is around to hear it, it didn't fall.
4. Every developer in the world wakes up thinking I should build a to-do list app and people love jumping between productivity apps and workflows. There is no moat in productivity--avoid it if you can.
5. Running a SaaS business without deeply understanding churn, LTV, CAC etc, is like flying a plane without instrumentation--really stupid and dangerous.
6. Failure sneaks up on you slowly, then all at once.
7. R&D is EXPENSIVE. Especially when competing with venture.
8. If you're competing on features, it never stops and is an ever-increasing line item.
9. Good product with great marketing beats amazing product with no marketing.
10. Bootstrapping works best in uncompetitive spaces/niches or if you have an unfair advantage (a personal brand, unique customer acquisition channel, etc).