RAG Demo Dataset · v1.0

BrewPulse Coffee

Synthetic operational corpus for Retrieval-Augmented Generation demos. Eight interconnected documents simulating a real enterprise knowledge base — where no single file answers any meaningful question alone.

AI-generated, manually curated. Designed with deliberate retrieval failure modes: indirect references, multi-hop causal chains, and ambiguous attribution.

8Corpus Files
5,100Words
20Demo Queries
201Entities
175Relationships
12Recurring Entities
01

Corpus Structure

01_north_regional_ops_report.md

North England Regional Operations Report — March 2024

Regional Ops Report

Sarah Mitchell's overview of Leeds Central and Manchester Piccadilly. The entry-point document that surfaces the core problem cluster without fully explaining any single issue.

LeedsManchesterNorthBrewoat milkBar 2

02_incident_leeds_espresso_failure.md

Incident Report — Espresso Machine Failure, Leeds Central

Incident Report

Formal incident log INC-2024-0312 by duty manager Daniel Park. Precise timeline of the Bar 2 valve failure. Key technical anchor for cross-document reasoning.

INC-2024-0312La MarzoccaMarcus Webbvalve seal

03_supplier_northbrew_oat_milk.md

Supplier Update — NorthBrew Supplies Oat Milk Disruption

Supplier Update

Dominic Ferrara's account of the Wakefield depot logistics failure. Documents a previous Sep 2023 incident — critical for establishing recurrence.

NorthBrewWakefieldDominic FerraraGreenLeaf

04_customer_feedback_north.md

Customer Feedback Summary — Leeds & Manchester

Customer Feedback

Amara Osei's March compilation. 47 submissions, 62% negative. Connects "watery espresso" to equipment faults — without naming the root cause.

Amara Oseiespresso qualitymobile ordering61.7% negative

05_staffing_issues_north.md

Staffing Issues Report — North Region, Q1 2024

Staffing Issue

Sarah Mitchell & HR partner Gemma Holroyd's Q1 assessment. Tom Okafor resigned, Priya Nair transferred. Identifies pay gap and shift patterns as structural drivers.

Tom OkaforPriya NairGemma HolroydSheffield

06_maintenance_report_north.md

Maintenance Report — North England Branches, March 2024

Maintenance Report

Marcus Webb's technical log. Confirms the same valve failure class at both Leeds and Manchester — a pattern invisible in any other single document.

Marcus WebbBP-LC-EM02solenoid valveboiler

07_regional_performance_q1_north.md

Regional Performance Summary — North England Q1 2024

Performance Summary

KPI review: Leeds CSS dropped 3.8→3.1 (steepest recorded decline). Manchester mobile adoption 23% but 18% complaint rate weeks 1–2. Sheffield as control case.

CSS 3.1transactions -13%Sheffield +2%Q1

08_logistics_mobile_ordering_disruption.md

Logistics & Technology Disruption — Mobile Ordering Rollout

Logistics Report

Lena Frost's post-implementation analysis. Documents the Orda POS modifier sync bug and its 2-week fix lag. Bridge document linking supplier to technology thread.

Lena FrostOrda POSmodifier syncoat milk bug
02

The Central Causal Chain

This four-hop chain spans four files — the kind of reasoning that requires multi-document retrieval to reconstruct. No single document tells this full story. This is Query 20 in the demo: the wow highlight.

Wakefield depot failure → Google Review complaint

Wakefield depot systems migration fails

file 03

40% oat milk shortfall at Leeds Central

files 01, 03

Mobile oat flat white order unfulfillable

file 08

Formal complaint + Google Review posted

file 04

Why this matters: Graph traversal reconstructs the full chain by following entity links (NorthBrew → Wakefield → oat milk shortage → mobile order → complaint). Semantic search retrieves isolated fragments — it finds the complaint and the depot failure, but cannot reliably bridge all four hops.

03

Entity Cross-Reference Map

Named entities act as retrieval anchors. The more files an entity appears in, the more it can bridge unrelated-seeming documents during graph traversal.

EntityTypeReferenced in Files
NorthBrew Suppliessupplier
0103040708
Sarah Mitchellperson
010203050607
Leeds Centralbranch
0102030405060708
Manchester Piccadillybranch
0104060708
Espresso machine failureincident
0102040607
Oat milk shortagesupply
010203040708
Mobile ordering rollouttechnology
0104050708
Staffing shortagehr
01040507
Marcus Webbperson
0206
Dominic Ferraraperson
030708
Amara Oseiperson
0407
James Rowleyperson
0108
04

20 Demo Queries

All 20 questions require retrieval across multiple documents. None can be answered correctly from a single file. Grouped by theme for demo navigation.

Supplier & Supply Chain
  • 01Which operational issues were directly caused or worsened by the NorthBrew Supplies disruption?
  • 02What branches were affected by the oat milk shortage, and what were the downstream consequences at each?
  • 03Has NorthBrew Supplies caused supply problems before, and how does the March 2024 situation compare?
  • 04What steps has BrewPulse taken to reduce dependency on NorthBrew Supplies?
Equipment & Maintenance
  • 05Which branches experienced espresso machine failures, and what is the common root cause?
  • 06What is the relationship between the Leeds Central and Manchester Piccadilly equipment faults?
  • 07Are the espresso machine issues at Leeds and Manchester likely to recur at other branches?
  • 08What maintenance actions are currently outstanding and which carry the highest operational risk?
Mobile Ordering Rollout
  • 09What problems emerged after the mobile ordering system launched in North England?
  • 10Why did the oat milk ordering bug take two weeks to fix, and what was the customer impact?
  • 11How did the timing of the mobile ordering rollout interact with other operational problems?
  • 12What should be done differently before the Midlands cohort rollout in May?
Staffing
  • 13Which branches had staffing shortages in Q1 2024, and what caused them?
  • 14How did understaffing at Leeds Central compound the impact of the equipment failure?
  • 15What is the risk to Easter trading given current headcount levels?
Customer Experience
  • 16Which cities mentioned both staffing shortages and customer complaints in the same period?
  • 17What is the connection between the espresso machine fault and customer complaints about drink quality?
  • 18Which customer complaints can be traced back to a supplier issue rather than a branch-level failure?
Cross-Document Reasoning
  • 19If you were the Head of Operations reviewing Q1 2024, what would you identify as the single most important systemic risk to address?
  • 20Trace the full chain of events from the NorthBrew Supplies Wakefield depot failure through to the Google Reviews complaints at Leeds Central.
05

Retrieval Challenge Design

Six deliberate design properties ensure the dataset rewards multi-document retrieval and punishes naive keyword search or single-document lookup.

🔗

Indirect References

Causes and effects are named differently across documents. The system must bridge vocabulary gaps semantically.

"Watery espresso" complaints in file 04 ← valve pressure failure in file 02 — never explicitly linked.
⛓️

Multi-Hop Causal Chains

The full cause-effect story spans 3–4 documents. Single-document retrieval gives an incomplete and potentially misleading answer.

Wakefield depot → oat milk shortage → mobile order fail → Google Review. Files 03→01→08→04.

Ambiguous Attribution

Some complaints could plausibly be blamed on the app, the supplier, or the equipment. Only multi-doc retrieval disambiguates.

Was the Manchester oat milk complaint about the POS bug or the NorthBrew shortfall? Answer: both, in different weeks.
📅

Timeline References

February events appear in March documents as assumed context. The system must reconstruct timelines across report dates.

The fault "first noticed mid-February" in file 02 is the same event described as a "six-week issue" in file 01.
🧩

Partial Information

Each document holds a piece of the puzzle. A correct answer requires synthesising fragments from 2–5 files.

Leeds fault: described technically in 02, operationally in 01, impact in 04, fleet risk in 06, KPI outcome in 07.
🏆

Control Case (Sheffield)

Sheffield's good performance is explained by a decision documented across two separate files — requiring synthesis to understand why.

Rosa Chen's buffer stock decision (file 07) traces back to the Sep 2023 NorthBrew disruption (file 03).
06

Dataset Methodology

BrewPulse Coffee is synthetic — generated with Claude and manually curated. This is disclosed openly because the methodology itself demonstrates the engineering skill, not a limitation to hide.

Generation

AI-assisted synthetic corpus design

Documents were generated with Claude, co-designed with deliberate retrieval failure modes in mind. Entity recurrence, vocabulary gaps, and multi-hop dependencies were specified upfront — not left to chance.

Curation

Manual curation and ground truth

Each of the 20 queries has a manually verified ground truth mapping: expected files, expected retrieval method winner, and the reasoning. This enables precision/recall evaluation of any retrieval change.

Extraction

Custom graph extractor (not off-shelf)

Graphify v0.8.13 was tested and rejected — 30–40% entity recall and a streaming bug. A custom extractor was written using Claude tool use with domain-specific entity typology and confidence scoring. Build cost: $0.11.

Embedding

File-level chunking via Voyage AI

Documents are short (~640 words). File-level chunking is used — no sliding window needed. Voyage AI voyage-3 embeddings stored in pgvector on Supabase. Total embedding cost: $0.0004.

Ready to explore the retrieval?

Try the 20 queries live — see graph vs semantic side by side.

Try the Demo →