I built AI-native analytics that lives inside your AI coding assistant — here's what 3 months of dogfooding taught me

"The gap wasn't analytics, it was access" is the sharpest line, and "questions force a decision, dashboards are passive" is actually your moat. You're not competing with Plausible or Fathom on features, you're competing on whether the data gets used at all. Better fight. Every dashboard fights to be the tab you open; you win by removing the tab.

What makes it defensible: it only works living where the decision happens. Someone shipping in Cursor asks "did that help?" in the same window, no context switch, so they act. A standalone dashboard can't copy that without becoming you.

To your question: it's the never-visited tab, always. What % of active users ask a question in week two, not just week one? That tells you if the habit forms.

This is the core insight: your measurement system determines which data becomes signal and which becomes noise. A dashboard is a measurement system that lives outside your workflow—it exists but doesn't get visited. The MCP tool is a measurement system that lives inside your decision-making loop—the question gets asked because it doesn't require a context switch. The analytics data was identical in both cases; what changed is whether it led to action. I'd measure this directly: for each spike you flag with the MCP tool, track whether you changed distribution, product, or onboarding within 7 days. That tells you whether Amami is becoming a real growth lever or just better access to data nobody changes decisions from. The launch-day vs launch-week observation is the same pattern: channel volume is noise without the second-week retention metric that tells you which visitors actually stayed.

The dogfooding result points to an access problem, not a reporting problem. I’d measure the behavior change directly: for the same user, compare how often they ask a question and take a follow-up action versus how often they open a dashboard and do anything within the next day. That would separate “this is convenient” from “this changes decisions.” Your launch-day versus launch-week observation is a useful warning too—I'd segment channels by second-week return rate and the first meaningful action, not just visits. One question I’d test next: when the assistant surfaces a spike, do users change distribution, onboarding, or the product itself? The answer may tell you whether Amami is becoming analytics access or a real growth workflow.

The interesting signal here is that the dashboard may not actually be the product problem — the access pattern might be. If asking a question inside the coding workflow consistently leads to more action than opening analytics separately, that feels like a much bigger shift than simply adding an MCP interface. Curious how consistently you've seen that behavior outside your own dogfooding.

The 'dashboards are passive consumption' line is the one that matters. I shipped a small tool for myself once, same pattern — data existed, I never looked at it, because looking at a chart wasn't an action. The moment something asks me a question ('why did traffic spike?') it forces a decision, and that's when I actually change something. Also seconding the launch-day vs launch-week point: one burst of curious visitors told me almost nothing, a handful of users who came back next week told me everything. Channel quality beats channel volume every time.