AI first-draft renewal briefs (L1)

Before every renewal call the CSM pastes the account's last three tickets, last QBR notes, and usage summary into the sanctioned assistant and gets a one-page brief: what they bought, what they use, what is broken, what to ask. No integration, no automation, one shared prompt.

WORKFLOW1Write one renewal brief p…omptChatGPT2Define the paste kitManual3Run it on the next ten re…ewalsManual4Fix the prompt from the m…ssesChatGPT
4 steps, in order, with the tool that owns each one.
Adoption ladderSix levels from Starter to Rebuilt. This item sits at level 1.L1 StarterOne tool, no workflow changeL2 AssistedAI drafts, humans approveL3 IntegratedWired into CRM and SlackL4 OrchestratedMulti-step, owned, measuredL5 AutonomousAgent runs, human auditsL6 RebuiltThe process itself changes
This playbook belongs at L1 Starter. Running it above your level is how pilots stall.
Measures of success% renewals with a brief; CSM prep time per renewal; brief useful ratePROVE IT WORKED% renewals with a briefCSM prep time per renewalbrief useful rate

The steps

  1. 01

    Write one renewal brief prompt

    Tool: ChatGPT

    Six fixed sections: contract summary, adoption signal, open issues, executive sponsor status, expansion angle, three questions to ask. Store it in the shared prompt library so every CSM uses the same skeleton. Owner: CS leader. Time: one afternoon. DoD: the prompt is in the library and linked from the renewal checklist.

  2. 02

    Define the paste kit

    Tool: Manual

    Tell CSMs exactly what to paste: last three support tickets, last QBR notes, the usage export, and the renewal date. Garbage in produces a confident brief about nothing. Pitfall: pasting raw customer PII into an unsanctioned tool. Use the approved assistant only. DoD: the paste kit is one screenshot in the CS handbook.

  3. 03

    Run it on the next ten renewals

    Tool: Manual

    Each CSM produces a brief for their next ten renewal calls and marks it useful or not useful in a shared sheet. You are measuring whether the brief changed a single question the CSM asked. Owner: each CSM. DoD: ten briefs scored, with one line on what the brief missed.

  4. 04

    Fix the prompt from the misses

    Tool: ChatGPT

    Read the not useful rows. Most failures are missing input, not a weak model. Add the missing input to the paste kit or tighten the section that produced filler. Owner: CS leader. DoD: version two of the prompt is published with a changelog line.

Tools in this playbook

Next playbooks

Unfamiliar terms are defined in the AI and Revenue Dictionary. Related frameworks live in the framework library.

Share this playbook

Posting to Instagram or TikTok? Copy the link, it carries the title, summary and share image.

Arrives weekly by email. Free. Unsubscribe anytime. By subscribing you agree to our Privacy policy and Terms. We never sell or share the list.