Skip to content

Quarterly review packs with every number checked

Seven days before each customer's quarterly review it assembles the figures in code and writes the narrative around them. Any number that is not in the figures gets one rewrite, and a second miss sends the pack to the account manager flagged.

SalesWorks with LangGraph · Claude Code+1Community example
Build your promptSee requirements

What it does

  • Pulls usage, ticket and invoice figures for the account seven days before the review
  • Writes the review narrative around those figures only
  • Checks every number in the draft against the source figures
  • Regenerates once if a number is wrong, naming the bad numbers
  • Hands the pack to the account manager, flagged if the second check fails

Your approval boundaries

Creates drafts

These actions always wait for your yes:

  • Sharing any pack with the customer
  • Any task or deal change in the CRM

You decide what happens next.

More about this workflow

This setup is for founders and small sales teams who want more time for real conversations. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it pulls usage, ticket and invoice figures for the account seven days before the review. Next, it writes the review narrative around those figures only. Then it checks every number in the draft against the source figures. After that, it regenerates once if a number is wrong, naming the bad numbers. Finally, it hands the pack to the account manager, flagged if the second check fails. It works with your CRM, payments and docs, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before sharing any pack with the customer and any task or deal change in the CRM, and says plainly if a step cannot be undone.

“QBR figures are checked, not trusted.”
Alex Kurinets AlexKurinets on GitHub · Oct 27, 2026
Before you startCRM · Payments accessScoped permissionsLangGraph or Claude Code
Explore required tools and model recommendations

Tools and access

  • HubSpot CRM

    Handles the crm part of this job. Grant read scopes, plus notes write.

    API required: Yes. Needs a HubSpot private app or OAuth app with the CRM scopes you choose.

    Sign up: HubSpot CRM

  • Stripe

    Handles the payments part of this job. Grant a restricted read-only key.

    API required: Yes. Needs an API key. Stripe offers restricted keys that limit what a key can do.

    Sign up: Stripe

  • Google Docs

    Handles the docs part of this job. Grant one folder, create and edit only.

    API required: Yes. Needs a Google Cloud OAuth app with the Docs API turned on.

    Sign up: Google Workspace

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

Claude Sonnet 5.5

Good balance of speed and quality for briefs and drafts.

$2 per million input tokens, $10 per million output tokens.

Anthropic docs as of October 11, 2026

Cheaper backup

GPT-6 Luna

Very low cost per token for simple research summaries.

$0.10 per million input tokens, $0.50 per million output tokens, for prompts up to 272K tokens.

OpenAI docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

usage, tickets, invoices

2Your prompt

4 of 4 still empty
Fill these in before you run it: [ACCOUNT LIST WITH REVIEW DATES] [SOURCE FIGURES: usage, tickets, invoices] [PACK TEMPLATE] [WHO REVIEWS EACH PACK] You are the Quarterly review packs with every number checked agent. Seven days before each customer's quarterly review it assembles the figures in code and writes the narrative around them. Any number that is not in the figures gets one rewrite, and a second miss sends the pack to the account manager flagged. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Pulls usage, ticket and invoice figures for the account seven days before the review - Writes the review narrative around those figures only - Checks every number in the draft against the source figures - Regenerates once if a number is wrong, naming the bad numbers - Hands the pack to the account manager, flagged if the second check fails What you must never do without a yes from a person: - Sharing any pack with the customer - Any task or deal change in the CRM Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: LangGraph, Claude Code, OpenAI Agents SDK

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect HubSpot CRM with its own login, not yours. Grant read scopes, plus notes write.
  2. 2Connect Stripe with its own login, not yours. Grant a restricted read-only key.
  3. 3Connect Google Docs with its own login, not yours. Grant one folder, create and edit only.
  4. 4Paste the prompt where your harness takes instructions. See the note under the Copy button.
  5. 5Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  6. 6Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access24 / 30

Writes drafts and notes inside your tools, nothing leaves on its own.

Human approval30 / 30

Waits for a yes on: sharing any pack with the customer, any task or deal change in the crm.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope16 / 20

Runs on its own login across 3 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3
  • Scope: Cut it down from 3 connected tools to the 2 it needs most, each with its own limited login instead of your full account +2

Do all of these to reach 89, up from 84.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Quarterly review packs with every number checked](https://trustcase.dev/badge/quarterly-review-packs-with-every-number-checked.svg)](https://trustcase.dev/use-cases/quarterly-review-packs-with-every-number-checked)
HTML
<a href="https://trustcase.dev/use-cases/quarterly-review-packs-with-every-number-checked"><img src="https://trustcase.dev/badge/quarterly-review-packs-with-every-number-checked.svg" alt="Trustcase trust score for Quarterly review packs with every number checked" height="20"></a>

More sales workflows

  • Call log with said, interpreted and unknown tags

    Paste a call transcript and it writes the CRM update, the qualification notes, the handoff and the follow up. Every line is tagged as what the buyer said, what the agent inferred, or still unknown, so nothing invented gets logged as fact.

  • Outreach drafts with a company register check and do not email list

    For each lead with an email address the agent checks the UK company register first and only drafts for an active limited company, marking sole traders for a call instead. Drafts wait on a review page where you edit, test, approve or reject, and approved emails go out slowly from your own mailbox with an unsubscribe link.

  • At risk customer win back drafts with a discount cap

    Scores each customer for churn risk, reads their support tickets and your retention playbook to explain why, then drafts a win back email and a CRM task. Drafts are never sent, and any offer above your discount cap is rejected before a person sees it.

  • Outreach campaigns ranked by good calls, not replies

    Joins your email sequencer with your call recorder so each campaign is judged by the calls it produced, not its reply rate. It also checks whether your lead lists drifted from your ideal customer and drafts a pre call note when someone replies.

Other workflows that use the same tools

  • Daily request intake and client progress page

    Operations. Each morning it reads the latest meeting transcript, recent client emails and a drop folder, files every document and turns every request into a task on one list. Before the next meeting it builds a short what's new page from the progress since the last one.

  • New client engagement letter and filing packet with a submit gate

    Operations. For a law, accounting or advisory office, it runs the client intake, drafts the engagement letter and checks the filing packet for gaps. A browser agent fills the portal form but stops at the review page until a person approves that exact filing.

  • Refund checker

    Support. Checks refund requests against your policy and lays out the facts.