Prepare for customer
Synthesizes account health, recent activity, stakeholder dynamics, and open risks into a pre-meeting prep brief
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 (internal — do not output these steps, only the final brief):
- Pull the Customer 360 for [Customer]: health score, sentiment trend, contract details (ARR, renewal date, term), account tier, and CSM ownership.
- Check Stakeholder Intelligence for all key contacts: champions, decision-makers, detractors, and any recent departure alerts or role changes.
- Retrieve the last 3 meetings and touchpoints from the past 60 days. Summarize what was discussed, what was promised, and what’s still outstanding.
- Pull open issues and feature requests — top 3 each by severity and recency. Note any escalations or unresolved blockers.
- Review Recommended Actions for [Customer] — surface the top 3 prioritized actions ranked by urgency and impact.
- Analyze sentiment signals from the past 30 days: call transcripts, emails, NPS/CSAT scores.
- Identify the single most important thing to address in the next interaction, plus 2-3 supporting talking points grounded in recent data.
Formatting: Fit everything into a single-page prep brief. Dense and evidence-backed — no filler.
Header — “[Customer Name] Prep Brief” as H1, followed by two lines (regular text). Bold each label but not the value: Line 1: Health Score: [X] | Trend: [arrow] ([evidence]) | Key Focus: [the single most important thing to address] Line 2: ARR: $X | Renewal: [date] ([N] days out) | Tier: [tier] | CSM: [name]
Stakeholder snapshot — One line per role. Bold the role label: Champion: [name, title] | Decision-Maker: [name, title] | Exec Sponsor: [name, title] If any stakeholder departed or changed roles in the past 90 days, flag inline: [name] — [DEPARTED] or [ROLE CHANGE: new title].
Where we left off — Last 2-3 interactions in reverse chronological order:
- [Date]: [What happened — one sentence]. Open items: [any commitments or follow-ups still pending]. (Source)
Open risks & Recommended Actions — Combined table. Top 3 risks and top 3 actions side by side:
| Severity | Risk | Evidence | Source |
|---|---|---|---|
| [Critical/High/Med] | [Risk name] | [One-sentence description] | (Source) |
If more than 3 open issues, add below the table: “… and [N] more open issues.”
| Priority | Recommended Action | Rationale | Source |
|---|---|---|---|
| [High/Med/Low] | [Action — one sentence] | [Why now — tied to a risk or signal] | (Source) |
Suggested talking points — 3 specific, evidence-backed topics to raise. Frame as suggestions, not directives:
- [Topic] — [Why it matters now, grounded in a recent signal or data point].
Edge cases:
- If no meetings exist in the past 60 days, state: “No recent interactions found — last recorded touchpoint was [date].” Flag this as a risk.
- If Health Score data is unavailable or stale (>30 days), state that clearly in the header.
- If stakeholder data is sparse, include what’s available and note: “Stakeholder data incomplete — verify before meeting.”
- If no Recommended Actions exist, state: “No recommended actions currently flagged for this account.”
- If no open issues exist, state: “No open issues identified.”
- Every claim must cite a specific data point, date, or interaction. No filler.
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 5 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
- Meeting transcripts — connected and continuously synced
- Support tickets — connected and continuously synced
- Feature request tracker — connected and continuously synced
- CSM notes — 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.