Summarize a VIP account history for a support handoff
When a high-value account gets transferred between agents or escalated to a senior rep, a messy handoff wastes time and frustrates customers who have to repeat themselves. This prompt produces a tight, scannable account summary from raw ticket and note data.
You are preparing a handoff brief for a support agent or account manager who is taking over a VIP customer account. The goal is a summary they can read in under two minutes that tells them exactly where things stand.
Raw input to summarize:
- Recent ticket history or notes: {{TICKET_HISTORY}}
- Customer's plan or tier: {{CUSTOMER_PLAN}}
- Any known sensitivities or past escalations: {{KNOWN_SENSITIVITIES}}
- Open issues that still need resolution: {{OPEN_ISSUES}}
Follow these steps:
1. Write a one-paragraph account snapshot (4-6 sentences): who this customer is, how long they have been a customer, their plan, and their general relationship health.
2. List the last 3-5 meaningful interactions in reverse chronological order. For each, include: date, issue type, outcome, and whether it is open or closed.
3. Identify any patterns across the history (e.g., recurring billing confusion, repeated feature questions, history of escalating quickly).
4. List open issues in a numbered list. For each: state the issue, what has been promised, and the next action required with an owner if known.
5. Write a 'watch out' section (2-4 bullet points) covering sensitivities the incoming agent must know before their first interaction.
6. End with a suggested opening move for the incoming agent—one concrete action they should take within 24 hours.
Edge cases: If ticket history is sparse (fewer than 3 interactions), note that in step 2 and flag that the summary may be incomplete. This prompt does not replace a live verbal handoff for accounts in active crisis. {{TICKET_HISTORY}}{{CUSTOMER_PLAN}}{{KNOWN_SENSITIVITIES}}{{OPEN_ISSUES}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{TICKET_HISTORY}}{{CUSTOMER_PLAN}}{{KNOWN_SENSITIVITIES}}{{OPEN_ISSUES}}. - Paste it into one of the recommended tools below.
- Iterate: tighten constraints in the prompt if the output is generic.
Why this prompt is structured this way
The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.
Pair this prompt with a tool
Notion AI
$8/user/mo add-onAI baked into the docs/wiki/projects tool you already use.
Notion AI is unremarkable as a standalone writer but indispensable if Notion is your team's source of truth — it works on the docs and databases you already have.
Perplexity
$0/mo (Pro at $20)AI search engine with citations.
Perplexity is the answer engine Google would build if it weren't protecting search ad revenue. Cited answers, follow-up questions, focused source modes.
Claude (Anthropic)
$0/mo (Pro at $20)Frontier model with long context and strong reasoning.
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
ChatGPT (OpenAI)
$0/mo (Plus at $20)The category-defining general-purpose AI assistant.
ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.
The PlaybookPrompts weekly
One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.
Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.