Ramp의 AX (회사를 AI로 물들이는 법)

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.

Some tools must choose to be dumbed down. PKM tools are one example.

There is a repeated paradigm in the Tools for Thought Software as a Service market. They are too complicated to use. Calendars, Objects, Comments, Backnotes, Blocks, Tasks, etc, etc, etc...

To pull out the most from these tools, you must first grow some skillfulness in these tools and aggregate enough information over a threshold. For team tools, you must ensure this for every member. If you're choosing a tool based on what features it includes, instead of where it can take you, it's like when you prepare for an exam, you try to make a perfect note instead of actually studying.

To successfully harness the productivity tool, you must flow at one point. Tools and infra fade out, and you only focus on the content. Our brain must outpace the tool; our brain must work more than the tool. Even Notion is too complicated for personal task management.

Based on my experience, tools must have the minimum friction, only having...

• Journal. You write daily notes.
• From there on, highlight keywords by adding double brackets.
• Regularly explore the double-bracketed keywords. Write more details.
• Voila! You realize that things are interrelated in a way you never imagined.

Out of intense complexities, intense simplicities emerge. -- Winston S. Churchill

Supergravity Products