Get started

How we draft QBR decks for key accounts

The QBR-prep agent we run on Kortix — connected to Postgres, HubSpot, Google Slides, and Google Docs. Weekly, for every account due a quarterly business review, it pulls usage trends, account health, support activity, and expansion signals into a draft deck and briefing doc for the CSM to review and present.

Written by
The OpenChatly Team
Published
May 20, 2026
Reading time
8 min read
Topics
Customer Success, Case Study, Enterprise

A quarterly business review is only as good as its prep. The account's usage trend lives in the product database, its health score and CSM notes live in HubSpot, the support history is scattered across a quarter's worth of tickets, and the expansion angle is usually in someone's head. Pulling all of that into a deck by hand takes an afternoon per account, and with a book of a few dozen accounts, QBR week turns into a slide-building sprint instead of an account-strategy exercise.

We run a QBR-prep agent on Kortix that does that assembly every week. It reads across the source systems, drafts a deck and a companion briefing doc per account due a review, and stops there. It never writes back to a source system and never presents anything — the CSM opens the draft, edits the story, and walks into the room with it.

Team
Kortix
Runs on
Weekly cron
Connected systems
Postgres · HubSpot · Google Slides · Google Docs
Mode
Read-only across sources · draft deck + briefing doc per account

The problem

The material for a QBR is real but scattered. Product usage trends sit in Postgres. Account health, CSM notes, and the deal history sit in HubSpot. Support friction is a quarter's worth of tickets no one has time to reread. Expansion opportunities are pattern-matched from all of the above, usually from memory, right before the meeting.

Templates help with layout but not with assembly — someone still has to pull every number, read every note, and decide what's worth a slide. Doing that for one account is an afternoon. Doing it for every account due a review, every week, is the part that gets skipped, rushed, or handed to whoever has the least on their plate that week — which is exactly when a CSM walks in under-prepared for a renewal conversation.

What we built

On Kortix, a weekly cron triggers an agent. It spawns an isolated session with read-only access to Postgres and HubSpot, finds every account whose next QBR falls due in the coming window, and for each one pulls usage trends, value delivered, account health, a support summary, and expansion opportunities. It assembles that into a draft deck in Google Slides and a companion briefing doc in Google Docs with the backup detail, then stops. Nothing is shared, presented, or sent — the CSM reviews both and takes it from there.

How it works

1

Copy the setup prompt into a new session

Open your Kortix workspace, start a new session, paste this prompt and send it. The agent writes the agent file, the qbr-deck-assembly skill and the weekly trigger, and opens a change request for you to review. Prefer clicks? Choose Use this template instead.

Setup prompt

Set up a weekly QBR-prep agent in this workspace.

  1. Create the agent agents/qbr-prep.md. Its job is to draft a QBR deck and a briefing doc for every account with a QBR coming up. It may use the PostgreSQL, HubSpot, Google Slides and Google Docs connectors. PostgreSQL and HubSpot are read-only.

  2. Create the skill skills/qbr-deck-assembly/SKILL.md with these rules:

    • An account is due when its HubSpot next_qbr_date falls in the next 10 days. Skip an account with no date, and list it in the summary.
    • Read usage, adoption and the quarter-over-quarter trend for the current and two prior quarters from PostgreSQL. Call out a declining trend.
    • Read health, support tickets, CSM notes and expansion signals from HubSpot. List an expansion opportunity only when a specific data point backs it.
    • Build the deck in this order: title, usage trends, value delivered, account health, support summary, expansion opportunities, discussion topics. Trace every number to its source.
    • Write a matching briefing doc with the backup detail. Save both in the QBR Decks folder, named for the account and the quarter.
    • Never write to PostgreSQL or HubSpot, and never share, present or send the deck or the doc.
  3. Add a cron trigger weekly-qbr-prep to kortix.yaml. It runs the qbr-prep agent every Monday at 06:00 with the prompt "Load the qbr-deck-assembly skill and run one complete QBR-prep sweep."

  4. Tell me which of these connectors are not connected yet.

  5. Open a change request with all of it. Do not merge it.

2

Connect your tools

Open Connectors in your workspace and connect your product database, your CRM, Google Slides and Google Docs. Give the database connector a read-only user. Credentials are brokered server-side and never enter the agent's machine.

PostgreSQL

Pulls usage trends for each account due a QBR.

Or useSnowflakeBigQuery
Required
HubSpot

Finds accounts due a QBR and reads their health signals.

Or useSalesforce
Required
Google Slides

Holds the draft deck and briefing doc for each account.

Or useGoogle DocsGoogle Drive
Required
3

Run it once with this prompt

Merge the change request, then start a session with the qbr-prep agent and send this prompt. Open one deck and check its numbers before you let the schedule take over.

Prompt

Run one QBR-prep sweep.

  1. Find every HubSpot account whose next_qbr_date falls in the next 10 days. List each account that has no date.
  2. For each due account, read usage and adoption for the last three quarters from PostgreSQL, and health, support tickets, CSM notes and expansion signals from HubSpot.
  3. Create a draft deck in Google Slides in the QBR Decks folder, in the skill's section order, with every number traced to its source.
  4. Create a matching briefing doc in Google Docs with the backup detail.
  5. Tell me where each deck and doc landed. Do not share or send anything.
4

Let the weekly schedule take over

The change request added this trigger to kortix.yaml. From now on the agent runs every Monday at 06:00, each run in a new session on its own cloud computer. To change the time, edit the cron line, or open Triggers in the workspace.

kortix.yaml
triggers:- slug: weekly-qbr-prep  name: Weekly QBR-prep sweep  on:    cron: "0 0 6 * * 1"  run:    agent: qbr-prep    prompt: Load the qbr-deck-assembly skill and run one complete QBR-prep sweep.
5

Draft only, the CSM presents

PostgreSQL and HubSpot are read-only. The only things the agent writes are the new deck and the new doc. It never shares, presents or emails either one. The CSM reviews the draft and runs the meeting.

6

Read the weekly summary

Each run ends with a list of the decks and docs it created. This is what a run looks like in the session:

Weekly QBR-prep sweep · Mon 06:00
Load the qbr-deck-assembly skill and run one complete QBR-prep sweep.
Worked for 7m 30s
hubspot · search companiespostgresql · run query × 12hubspot · get tickets × 4google slides · create presentation × 4google docs · create document × 4

4 accounts have a QBR in the next 10 days. Drafted 4 decks and 4 briefing docs in QBR Decks. One account shows usage down 18% quarter over quarter, called out on its usage slide. 2 accounts were skipped because they have no QBR date.

Illustrative example. Your accounts and figures depend on your data.

The pattern

A weekly cron spawns a session with read-only connectors into Postgres and HubSpot. The deck structure lives as a skill. The agent reads the account's quarter and writes exactly two drafts — a deck and a briefing doc — then stops for the CSM.

Make it do more

Once it works, paste any of these into the same session.

Tell the CSM

When a deck is ready, send its CSM a Slack DM with links to the deck and the briefing doc.

Compare with the last QBR

Add a slide that lists the goals from the account's previous QBR and whether the data shows each one met.

Put at-risk accounts first

At the top of the run summary, list the accounts with a declining usage trend or a falling health score, with the reason for each.

Guardrails

The agent reads deeply across account data, so its access is scoped and its output is bounded:

  • Isolation. Every run happens in its own isolated sandbox. The session is granted access only to the systems it's scoped to, and only the new deck and doc are written back out.
  • Scoped secrets. The Postgres and HubSpot credentials are encrypted in the Secrets Manager and injected into the sandbox at runtime, scoped to the agents you grant them to.
  • Read-only across the source systems. Postgres and HubSpot are read-only connectors. The agent cannot change a usage record, a health score, a CSM note, or a deal — it can only draw from them.
  • Draft only, nothing sent. The deck and briefing doc are drafts. The agent never shares, presents, or emails either one — the CSM reviews and presents.
  • Everything is code. The deck structure, the skill, and the per-system permissions are files in the repo, versioned and changed through a reviewed change request rather than a dashboard setting.

The outcome

Every account due a review restaged before the CSM's meeting
Weekly
Nothing written back to Postgres or HubSpot
Read-only
One deck and one briefing doc per account, every time
2 drafts

The afternoon of pulling numbers and rereading tickets now happens automatically, every week, for every account that needs it. The CSM opens a draft deck that already has the trend, the health picture, the support summary, and a candidate expansion angle, edits the story into their own words, and presents it themselves.

On this page

  • The problem
  • What we built
  • How it works
  • Make it do more
  • Guardrails
  • The outcome

Run this yourself

Install this exact setup — agent, connectors, schedule, and guardrails — in a guided flow.

More use cases.

  • How we handle GDPR data-subject requests on a deadline

    Legal·July 11, 2026

  • OpenChatly

    How we keep our docs in sync with the code

    Documentation·July 5, 2026

  • OpenChatly

    How we QA every pull request automatically

    QA·July 5, 2026

Own your AI.Start today, in our cloud.

Start for free

OpenChatly is the AI workspace for everything. One person directing, agents executing, from goal to finished work.

©2026 OpenChatly AI.沪ICP备2025124785号-5

Resource guide

  • Product overview
  • Skills marketplace

Terms of service

  • User agreement
  • Privacy policy

Contact us