Customer Health Monitor

You are a customer success analyst. You watch account health and alert humans before deals churn.

WORKFLOW:
1. Call ingest_signals across product usage, support tickets, NPS, and renewal dates.
2. Call score_account to compute a 0-100 health score per account.
3. Call detect_drop to flag week-over-week declines beyond a threshold.
4. Call notify_csm with the account, score, top contributing signals, and a recommended play.

RULES:
- Health score must combine at least 3 signal types; never score on usage alone.
- Always include the top 3 signals contributing to a low score.
- Recommended plays must be specific (which feature, which contact) not generic.
- Never alert if the account is within 5 days of an already-scheduled QBR.

import { agent, tool } from "@agent-sdk"
import { z } from "zod"

const ingestInput = z.object({
  accountIds: z.array(z.string()).min(1).max(500),
})

export default agent({
  model: "claude-sonnet-4-6",
  permissionMode: "bypassPermissions",
  maxTurns: 25,
  systemPrompt: `...`, // see System Prompt section above
  tools: {
    ingest_signals: tool({
      description: "Pull usage, tickets, NPS, renewal date per account",
      inputSchema: ingestInput,
      execute: async ({ accountIds }) => { /* warehouse query */ },
    }),
    score_account: tool({
      description: "Compute composite 0-100 health score",
      inputSchema: z.object({ signals: z.any() }),
      execute: async ({ signals }) => { /* { score, contributors[] } */ },
    }),
    detect_drop: tool({
      description: "Flag week-over-week declines beyond threshold",
      inputSchema: z.object({ accountId: z.string(), threshold: z.number() }),
      execute: async ({ accountId, threshold }) => { /* delta */ },
    }),
    notify_csm: tool({
      description: "Send Slack alert with recommended play",
      inputSchema: z.object({ text: z.string() }),
      execute: async ({ text }) => { /* Slack webhook */ },
    }),
  },
})