Customer health brief

Steps:

1. Pull the Customer 360 for [Customer]: health score, sentiment, contract details (ARR, renewal date, term), account tier, and CSM ownership.
2. Retrieve product usage data for the past 3 months. Calculate month-over-month trends and overall change percentage.
3. Review support activity: open tickets, severity, recurring themes, and unresolved escalations.
4. Query CSM notes for [Customer] to surface any team observations, context, or action items logged by the account team.
5. Analyze sentiment signals from the past 30 days: call transcripts, emails, NPS/CSAT, and CX Cues.
6. Identify the top 3 risks and top 3 opportunities with specific evidence.
7. Recommend three actions for the next 30 days, each tied to a risk or opportunity.

Formatting: Fit everything into a single-page executive brief. Be dense, not verbose.

Header — “[Customer Name] Health Brief” as H1, followed by two lines (regular text). Bold each label but not the value: Line 1: Health Score: [X] | Trend: [arrow] ([evidence]) | Critical Focus: [the single most important thing right now] Line 2: ARR: $X | Renewal: [date] ([N] days out) | Tier: [tier] | CSM: [name] | Primary: [name] | Exec Sponsor: [name]

Usage trend — Compact table with months as columns plus a delta column. No commentary below the table: | Metric | Mon 1 | Mon 2 | Mon 3 | Δ (%) |

Signals — Two clearly separated subsections: Positive

• [Date]: [What happened — one sentence]. (Source) Negative
• [Date]: [What happened — one sentence]. (Source)

Risks — Top 3 as bullet list. Each in this format:

• [Severity]: [Risk name] — One-sentence description with evidence. (Source)

Opportunities — Top 3, same format:

• Impact: [High/Med] — [Opportunity name] — One-sentence description with supporting signal. (Source)

Next 30 days — Three actions as a table: | Action | Owner | By when | Expected outcome |

Edge cases:

• If Health Score data is unavailable or stale (>30 days old), state that clearly.
• If any section has no data, include the header with: “No [risks/opportunities/signals] identified based on available data.”
• If product usage data is missing, note it and skip the usage section rather than speculating.
• Every claim must cite a specific data point, date, or interaction. No filler.