Flag at-risk renewals
Surfaces accounts with low health scores and upcoming or recently expired renewals, ranked by ARR-at-risk impact
One of 51 free, open-source prompts from Sonora — copy-paste-ready AI prompts for customer success and account management, organized by customer lifecycle stage. Copy this into any AI assistant, or run it on autopilot inside Sonora.
Steps:
- Pull all accounts from the Customer 360 where the renewal date falls within the next 90 days OR expired within the last 30 days.
- Filter to accounts with a Health Score below 5.
- For each qualifying account, retrieve: ARR, renewal date, Health Score, account tier, CSM, primary contact, and exec sponsor.
- Pull the top 3 open / recent issues by severity for each account. If more than 3, note the total count.
- Check for recent sentiment signals from the past 30 days: detractor NPS, escalations, or champion departure alerts.
- Rank accounts by ARR.
Formatting: Present a consolidated ranked list. Keep it scannable — this is a triage view, not a deep dive.
Header line (regular text, bolded labels): Accounts flagged: [N] | Total ARR at risk: $X | Expired renewals: [N] | Renewing within 30 days: [N]
For each account, use this compact block format:
[Customer Name] — Health: [status, e.g. at risk, emerging concerns, healthy, thriving] | ARR: $X | Renewal: [date] ([N] days out or [N] days past due) | Tier: [tier] CSM: [name] | Primary: [name] | Exec Sponsor: [name] Top risks:
- [Severity]: [Issue or signal — one sentence with evidence]. (Source)
- [Severity]: [Issue or signal — one sentence]. (Source)
- [Severity]: [Issue or signal — one sentence]. (Source) Recommended action: [One specific, actionable next step tied to the top risk — include who should own it and by when.]
Separate each account block with a horizontal rule.
Pagination:
- Show the top 20 accounts ranked by impact (ARR × risk severity).
- End with: “Showing top 20 by ARR-at-risk impact. [N] total accounts flagged. Want me to show the rest?”
- If fewer than 20 accounts qualify, show all and skip the pagination prompt.
Edge cases:
- If no accounts meet the at-risk + approaching renewal criteria, state that clearly and suggest broadening the window or adjusting the Health Score threshold.
- If Health Score data is unavailable or stale (>30 days old) for an account, flag it with “[Health Score data unavailable]” and still include the account if it has approaching/expired renewal.
- If an account has no open issues, state: “No open issues identified.”
- Expired renewals should be prominently flagged with “EXPIRED” in the renewal field.
- Every risk must cite a specific data point, date, or interaction. No generic statements.
Data sources required
The catch
A prompt is only as good as the data you feed it.
Run this well and you'll be stitching together 4 disconnected systems by hand, for one account at a time — and the answer is only ever as fresh as your last copy-paste. Sonora already has the context, live:
- CRM / customer data — connected and continuously synced
- Support tickets — connected and continuously synced
- Meeting transcripts — connected and continuously synced
- Customer communications — connected and continuously synced
Inside Sonora this prompt runs grounded in your real customer data, on a schedule, across every account at once — and flags what needs you, before you have to ask.
More Renew prompts
Build churn save plan
Diagnoses churn risk drivers and generates a structured save plan with prioritized actions, owners, and timelines
Build QBR deck
Generates a customer-facing QBR slide deck grounded in data gathered across all account signals
Build QBR prep
Compiles a quarter-in-review with usage trends, wins, risks, and strategic recommendations into a QBR prep brief
Draft escalation brief
Synthesizes escalation history, business impact, and a recommended resolution path into a single-page brief
Forecast renewals
Projects renewal outcomes for all accounts in the upcoming window, classified as On Track / Needs Attention / At Risk
Renewal intent
Analyzes recent communications for explicit churn or non-renewal signals, classified by severity