Cantrip AI
You built it. Now sell it. GoToMarket MCP server
No one is coming to save us. You've helped make companies millions or maybe even hundreds of millions with your former team.
AI is displacing us, but you've got real skills. You've got ideas. Maybe you've built a few things, but don't know how to get users.
I'm building Cantrip for you. There is no subscription. It's pay-as-you-go marketing expertise that gives you Claude a memory of your business and different marketing workflows to execute to learn how to get your first customer. You first 10, etc.
A subscription is the last thing you need when you're not working. But also, the future is agent-to-agent and pay-as-you-go. Subscriptions are a people-centric relic. (I may end up offering a subscription if it helps adoption, to wean people off of subscriptions).
We have to learn to be more entrepreneurial and self-sustaining because the old playbook of working for a Fortune 500 company is not coming back.
I'm doing a couple things that aren't wildly copied for Cantrip. They are all "old school", but useful and relevant for agentic coding and automated software factories.
Staging server - I deploy a full copy of my application to a staging server. For Cantrip that means:
MCP Server daemon is deployed to a staging server and taking traffic
MCP Server client supports an API endpoint override
Web dashboard is deployed to a staging server
I test with claude code session where the mcp server is configured to hit staging. I do automated testing against staging
One of the benefits is that my NextJs app in locahost is falky as files are changing and it is hot reloading. This way I can have a stable environment to QA in.
Clean Architecture - I use the clean architecture pattern. I identify "Ports" and make Adapters for those ports.
Example ports: LLM API call, DB Query, reading the system Clock or Filesystem
Adapters: I implement a Stub LLM API call and a Live LLM API call.
Why? I use Pact to record and playback executions. For example, I can record the entire inputs and outputs for a live LLM API call. These are written to a traces directory. Okay, so what?
1. I can replay these from the Stub adapter, making integration tests fast and deterministic
I can have an LLM troubleshoot an issue instantly as they can read traces of everything in detail.
What is your secret sauce for your automated software factory?
I made a demo of Cantrip.ai MCP Server capabilties.
We make a new business around "Cat food for humans and cats"
https://youtu.be/7ld5BLtgTIg
Comment