Team Onboarding Guide

The Fourth EBR Builder

How to produce executive business reviews that make hospitality leaders feel understood, show measurable impact, and create a clear path forward.

AI Enablement Team • April 2026

Why We Built This

The Old EBR Format Was Broken

Old Format

  • 30-40 slides of data dumps
  • Opens with Fourth's product pitch
  • Raw metrics without business context
  • No competitive benchmarking
  • Ends with a survey link

New Standard

  • 8-12 focused, outcome-led slides
  • Opens with the customer's world
  • Every metric tied to a business result
  • Live competitive intelligence built in
  • Ends with mutual commitments
Architecture

Two Claude.ai Projects, One Workflow

The system is split into two projects to keep each focused and within context limits.

1

EBR Processor

Parses your raw data files into a structured JSON package. Upload your workbook, Gong transcripts, SkyPrep exports, and Zendesk CSVs here.

Data Preparation
2

EBR Builder

Runs competitive research, plans the narrative, and generates a branded HTML presentation + PPTX. Paste your data summary here.

Presentation Generation

Why two projects?

The Builder's presentation engine (70KB component library, 166KB logo assets, themes, PPTX scripts) fills the context window. Keeping data parsing separate prevents Claude from forgetting presentation instructions mid-build.

Data Sources

Five Sources, One JSON Package

Source File Type What It Adds Priority
Macro Workbook .xlsm Core metrics: scheduling, labor, forecasting, engagement Required
Gong Transcripts .txt Customer voice, priorities, sentiment, quotes High
SkyPrep Training .csv / .xlsx Training completion rates, capability adoption Medium
Zendesk Tickets .csv Support partnership, resolution times, channel analysis High
Manual Metrics Pasted text Any metrics typed directly (fallback) Fallback

More sources = richer EBR. JSON only is good. JSON + Gong is better. All four file sources together produces the most comprehensive review.

Step 1 of 3

Gather Your Data

1

Export the macro workbook

From HotSchedules. Must be .xlsm with all 7 standard tabs. Refresh pivot tables in Excel before uploading.

2

Export Gong transcripts

Recent calls with the customer (last 1-2 quarters). Export as .txt files. Even 2-3 transcripts add significant depth.

3

Export SkyPrep training data

Completion reports filtered to the customer account. Save as .csv or .xlsx.

4

Export Zendesk tickets

Filter by organization and review period. Include ticket ID, category, channel, status, resolution time, and dates. Export as .csv (UTF-8).

Step 2 of 3

Run the EBR Processor

1

Open the EBR Processor project in Claude.ai

Start a new conversation for each customer EBR.

2

Upload all your data files

Drag in the .xlsm, Gong .txt files, SkyPrep exports, and Zendesk .csv all at once.

3

Tell it what to do

"Prep EBR package for Torchy's Tacos — QSR segment"

4

Download the output

You'll get two files: a .json data package and a .summary.md human-readable brief.

No source files? Skip the Processor entirely. Go straight to the EBR Builder and type or paste your metrics when prompted.

Step 3 of 3

Build the EBR

1

Open the EBR Builder project in Claude.ai

Paste the summary.md content. Upload the JSON if deeper analysis is needed.

2

Say: "Build an EBR for [Customer]"

The system detects your data, processes it, and starts the workflow.

3

Review at 3 checkpoints

Data Brief → Research Brief → Deck Plan. Approve or adjust at each step. Nothing is built until you say go.

4

Review HTML, then approve for PPTX

Open the HTML in your browser. Request changes. When satisfied, say "Approved" to generate the PowerPoint.

Your Controls

Three Checkpoints Before Build

The system never builds without your approval. You control the narrative at every stage.

1

Data Brief

Review what was extracted from your uploads. Confirm accuracy before research begins.

2

Research Brief

Review competitive and industry intelligence. Add context, flag sensitive information.

3

Deck Plan

Approve or reshape the narrative arc and slide outline. Changes are cheap here, expensive after build.

New: Zendesk Integration

What Ticket Data Adds to the EBR

Support Partnership Signal

  • Total tickets + average resolution time
  • Zero-minute resolutions = automated quick-fix efficiency
  • Channel breakdown (web, email, API, messaging)

Process Improvement Flags

  • Email channel violations (deprecated after Nov 2024)
  • Top ticket categories = training opportunities
  • Renewal tickets with product changes

Automatic Processing

No special commands needed. Upload the Zendesk CSV alongside your other files. The system detects it automatically, applies inclusion/exclusion rules, separates implementation tickets, and flags email channel violations.

Quick Reference

What to Say

What You Want What to Say
Start a new EBR "Build an EBR for [Customer]" / "QBR for [Customer]"
Run benchmarking "Yes, run benchmarking" (when offered)
Approve deck plan "Looks good, proceed" / "Build it"
Request changes "Change slide 3 to focus on forecasting"
Approve for PPTX "Approved" / "Looks good" / "Convert it" / "Go ahead"
Skip a phase "Skip research" (system will flag the tradeoff)
Best Practices

Tips for Better EBRs

1

The Deck Plan Is Your Steering Wheel

Checkpoint 3 is where you shape the story. Spend time here. Once you approve, the system builds exactly what you asked for.

2

Be Specific With Changes

"Move forecasting to slide 4 with a bar chart" is faster than "make it better." Specific requests = fewer revision rounds.

3

Don't Skip Research

The "Their World" slide is what makes the EBR feel personal. Without research, it becomes generic — and that's the old format.

4

The Recommendation Slide Matters Most

Executives remember the last thing they hear. Tie the recommendation to something the customer already said they care about.

Remember

A Fourth EBR should make a hospitality executive feel understood, show measurable impact, and create a clear path forward.

Product spelling: Fourth iQ — lowercase i, uppercase Q. Always.

Questions? Reach out to the AI Enablement Team.

Press or Space to navigate