Baremetrics
Day 34 after signup
I tested 15 prompts on our MCP, and these 3 are worth stealing
Copy, paste, and ask Claude about your MRR and churn
Why it works
- Open with a personal note and a specific reason the topic matters to the reader.
- Teach through concrete examples, then explain what to check or adapt before relying on the output.
- End with a small first step so readers can try the ideas without tackling the entire guide at once.
How it is built
- Personal monthly introduction
- Issue topic overview
- Three prompt walkthroughs
- Prompt setup guidance
Email copy
Hiya, there! It's Andrea here! How'd October treat you? 👀 This past month I connected Claude to a live Baremetrics account through our MCP, ran 15 prompts, and checked every answer against the dashboard. Three of them I'd hand to every founder on day one, because they turn jobs you already do into a single question. New to the Baremetrics MCP? It lets you ask Claude about your MRR, churn and customers in plain English, answered from your real Baremetrics data. It's read-only, so Claude can look but can't touch. Here's what we're covering today: The Monday metrics check, in one prompt A first-draft investor update (and the one line you should always double-check) The churn post-mortem that was my favorite test of all 15 Alright, grab your coffee and let's dive in. ☕ Check out all 15 prompts on the blog → Was this email forwarded to you? Subscribe Here 1. Your Monday metrics check, in one prompt You know the Monday routine. Open the dashboard, click through MRR, then cancellations, then trials, and try to remember what last week looked like. This prompt does the clicking for you: Using the Baremetrics MCP, compare MRR, new customers, cancellations and trial conversions for the last 7 days against the 7 days before. Tell me what changed most and whether anything looks unusual. Claude compares the last seven days with the week before, metric by metric The numbers are nice, but the commentary is the real win. When I ran this, Claude traced a jump in lost MRR back to a single day with several cancellations. Then it pointed out that some of those were annual plans that may simply not have renewed. It also flagged one metric that looked off and suggested checking the tracking before treating it as a business problem. That's the kind of thing I'd usually miss while skimming charts with my first coffee of the day. Pro tip: If you want something you can drop into Slack for your team, ask for a table at the end of your prompt. My first run needed a follow-up to get there. Set it up and try this prompt → 2. A first draft of your investor update The monthly investor update is mostly the same numbers in a new month. So let Claude gather them and write the first draft: Using the Baremetrics MCP, pull last month's MRR, net revenue, revenue churn and new customers, and compare each with the month before. Then draft a three-paragraph investor update: headline numbers, what drove the change, and what we're watching next month. The draft I got back was solid. But here's the part I want you to remember. One line said a dip in net revenue was down to billing timing. Underneath the draft, Claude added a "Before you send it" note flagging that this was its own inference (MRR went up while cash went down) and that it hadn't actually checked the charges. Under its draft, Claude flags its own unverified inference in a "Before you send it" note I loved that it was honest about it. And it's exactly the kind of sentence you should verify or cut before hitting send. So here's how I'd use this one: Let Claude do the gathering. It pulls every number and lays out the month-over-month changes in seconds. Rewrite the "why" paragraph yourself. Claude reads the data, but you know what actually happened that month. Check every number against your dashboard. Anything going to investors deserves a second look. Luke has been working this way too. In our monthly audit session with Claude, he said he likes that it lets him follow his train of thought instead of stopping to hunt for where a data point lives. Watch Luke's monthly audit with Claude → 3. The story behind your biggest cancellations This was my favorite test out of all 15, and it's the one I'd start with if churn has been keeping you up at night. When churn jumps, the first questions are always the same: who left, what were they paying, and what happened before they went? Answering that usually means opening customer page after customer page. Instead, run these two prompt