opsmarshal
Workflow 12 — RevOps Infrastructure

QBR Auto-Generation

Builds the value-realization story per account — usage against goals, ROI evidence, roadmap fit — as an on-brand deck the CSM edits and owns. Prep drops from a day to an hour, and no unreviewed slide ever reaches a customer.

At a glance

QBR Auto-Generation assembles the value-realization story per account — usage against goals, ROI evidence and roadmap fit — into an on-brand deck the CSM edits and owns, so no unreviewed slide reaches a customer. It is one of fifteen workflows in the Enterprise GTM Agent Stack, an Opsmarshal series on GTM stack architecture.

Owned by
CS Ops
Writes back to
Deck repo, CS platform, Audit log
Held to
−80% — Prep time per QBR
Gate
Permission → Evidence → Approval → Audit
Writes to: deck repo + CS platformApproval: CSM reviews every deckBrand: locked templates
Business Pain

Why this exists

The status quo

QBR prep eats a CSM day per account, so QBRs happen for the loudest 20% — and half of prep is hunting numbers that were true last quarter. The accounts that quietly needed the story never get one.

What this workflow changes

Every account gets a draft deck assembled from live data against its own success plan. The CSM's day becomes an hour of judgment — sharpening narrative, cutting what doesn't serve the meeting — and coverage stops being rationed.

Architecture

Reference architecture

Inputs
Success plansaccount goals and agreed baselines
Usage + outcome datalive, freshness-checked at generation
Benchmark cohortsaggregate-only, minimum cohort size
Agent Layer
Evidence Builderassembles the value case against the plan, balanced scorecard enforced
Deck Composerbrand-locked templates with lifecycle-stage narrative variants
Freshness Checkerblocks generation on stale data
Governance
Gate: permission → evidence → approval → auditevery deck reviewed and approved by its CSM before export · contractual data-sharing rules enforced per account · benchmark framing uses legal-approved blocks
Systems of Record
Deck repoversioned decks + approval state
CS platformQBR timeline + outcomes
Audit logapprovals, exports, exclusions
DecisionChoiceRationale
Draft, never finalThe deck ships to the CSM, not the customerA wrong number in front of a customer costs a renewal. Human review is enforced by the gate, not by policy hope.
Goals-anchored, not activity-anchoredDecks argue value against the success planUsage graphs without goal context are noise. If no success plan exists, the deck's first page says so — which is its own finding.
Live Demo

Run a scenario through the gate

Three curated scenarios — one that passes, one that flags for a human, one that the gate blocks. Watch the verdict, the evidence rows, and the audit log.

QBR Deck Composer

Governance audit log

[ready] agent idle — pick a scenario
Operator Control Panel

Someone has to run this thing

Agents don't remove operators — they change what operators watch. Console spec: who owns it, what they check, what pages them, and how they pull the plug.

QBR Auto-Generation — Ops Console

Owner: CS Ops

Daily monitors

  • Generation failures and data-freshness blocks

Weekly reviews

  • Edit-distance review — what CSMs consistently change becomes a template fix
  • Coverage rate — accounts getting QBRs vs. eligible

Alert thresholds → who gets paged

  • Deck exported without approval → sev-1
  • Stale data at generation → generation blocked, CS Ops notified

Manual controls

  • Template editor — brand-owned, versioned
  • Per-account data rules — what's contractually shareable
  • Kill switch — generation halts; approved decks untouched
Eval Metrics

What this workflow is held to

−80%
Prep time per QBR
CSM hours, before vs. after
QBR coverage rate
eligible accounts actually getting the story
0
Unapproved decks delivered
hard invariant from the audit log
Failure Modes

How it breaks, and what catches it

Metric cherry-picking

The composer leads with flattering numbers and buries the decline the customer already noticed. Mitigation: The template mandates a balanced scorecard section — declines render with the same prominence as wins.

Benchmark leakage

Cross-customer comparisons expose confidential patterns. Mitigation: Benchmarks only from aggregate cohorts above minimum size, framed with legal-approved blocks.

Template monotony

Every customer sees the same deck shape; it reads as mail-merge and devalues the meeting. Mitigation: Narrative variants per lifecycle stage; edit-distance telemetry drives template evolution.

Opsmarshal builds workflows like this one inside client stacks — see GTM stack architecture and AI enablement and agentic workflows, or book a call to walk through your own.

opsmarshal

Revenue Operations and AI Agentic Workflows for B2B companies in transformation. We build the machine. You run the company.

Services

Company

© 2026 Opsmarshal. All rights reserved. Privacy  ·  Terms