Customer Success

Account health that doesn't depend on gut feel

Customer success runs on signals scattered across Slack threads, warehouse tables, and audit logs. The data exists — it just isn't readable on a Tuesday morning before a QBR. These plans turn that scatter into scheduled, structured reporting.

Book a demo Browse every plan

What breaks when you do this by hand

The real state of an account lives in Slack threads nobody has a repeatable way to read.
Health conversations rely on gut feel because adoption and reliability data sits in tables no one queries by hand.
Tenant reviews mean a dozen ad-hoc queries reassembled into a deck, every time.

What you get instead

A single source of truth across usage, audit, and error data
Scheduled health reporting instead of pre-meeting scrambles
Relationship signals read consistently across every account

This is the whole thing

The opening of Customer Health Report — the system prompt, its typed parameters, and the tools it's allowed to reach, all declared up front. No canvas, no hidden nodes. 221 lines of source you can review in a pull request.

Read all 221 lines →

customer-analytics.fml

Copy

system("You are a CS and DevOps analyst generating a customer health report.")

parameter("tenant_id", type=string, title="Tenant ID")
parameter("customer_name", type=string, title="Customer Name")

require mcp BigQuery

components {
    schema("ServerStats") {
        mcp_name: string
        status: string
        total_tool_calls: int
        total_errors: int
        error_rate: float
        active_users: int
        distinct_tools_called: int
        active_days: int
        first_call: string
        last_call: string
        days_since_last_call: int
        connected_but_never_called: bool
    }

3 plans you can run today

Every one is a typed FML plan. Open it, read the source, and run it — nothing here is a mockup.

Customer Health Report

Customer health conversations rely on gut feel because adoption, usage, and reliability data is spread across warehouse tables no one queries by hand.

Customer success

Account teams

Ops

Read the plan