Context · The Ask · The Build · The System · Outcome · Reflection

Major Australian Bank · Personal Banking · 2026

From two weeks of manual reporting to a live dashboard in four hours.

A White Label Customer Experience team was spending two weeks every month rebuilding a 41-slide PowerPoint from ~30,000 complaints and NPS verbatims across nine brands. Copilot could not process more than 1,000 records at a time. I used Cursor to design and build a repeatable system: a live themed dashboard, an auto-generated executive report, and plain-English commands the team runs themselves. Monthly reporting dropped from two weeks to one day. This is a Generation-phase product on the Context Lifecycle.

AI Product Data Synthesis Cursor Customer Experience 0→1
My Role
AI Product Lead · Cursor build & handover
Stack
Cursor · Claude · GitHub Enterprise · enterprise design system
Organisation
Major Australian Bank · Personal Banking
Timeline
4-hour build · repeatable monthly workflow
Status
In use · Customer Experience team
Portfolio mockup of a Voice of Customer dashboard — overview with feedback trends, NPS, and theme breakdown. Illustrative data only.

Voice of Customer dashboard mockup — illustrative data, no bank branding. AI-synthesised complaints and NPS verbatims across partner and proprietary products.

Customer feedback at scale, trapped in a monthly rebuild.

Personal Banking's White Label portfolio spans nine partner brands plus proprietary products. Every month, the Customer Experience team needs a single, trustworthy view of what customers are saying: complaints, NPS verbatims, themes, subthemes, and month-on-month trends. Product owners and executives use that view to decide what to fix next.

The data existed. The problem was what it took to turn it into something useful. The team was rebuilding a dense, 41-slide PowerPoint from scratch every month. Manual work and Copilot could not keep up with the volume. Copilot hit a ceiling at roughly 1,000 records per pass. The real dataset was closer to 30,000 verbatims across nine brands, 23 themes, and 170 subthemes.

"We need a consolidated, real-time view with insights from a huge volume of customer feedback. White Label needs a single, clear view of what customers are saying across all nine brands, themes, trends, and patterns, in a format the business could actually act on. The data is there. The problem is what it takes to turn it into something useful."

— Customer Experience Lead · Partner portfolio · Personal Banking

One source of truth that would not take two weeks to create.

I joined this as an AI enablement build: take a real operational pain point, solve it with Cursor under enterprise AI guardrails, and hand the system back to the team that owns the data. The brief was not a prettier deck. It was a durable product.

~30,000
Complaints and NPS verbatims to process each cycle · nine brands · 23 themes · 170 subthemes
2 wks
Manual effort every single month · dense static output rebuilt from scratch
41
Slides in the monthly PowerPoint · the format executives knew, but could not scale

Six requirements, one system

01

One dashboard

A single source of truth. No monthly rebuild from scratch.

02

Themes and subthemes

Ranked, structured view of what customers are actually frustrated about, not just raw volume.

03

Month-on-month view

Move from static snapshots to trends: are things getting better or worse?

04

Actionable insights

Clear direction for product owners on what to do next, not just charts to interpret.

05

All nine brands

Switch between proprietary and White Label brands without rebuilding the analysis.

06

Reusable, repeatable process

A workflow the team runs themselves. Weeks of work compressed to hours.

Illustrative recreation of a manually rebuilt Voice of Customer PowerPoint — dense episodic NPS grid, product lines, partner brands, and complaint charts

Before: the manually rebuilt PowerPoint each month, taking two weeks every time. Episodic NPS, proprietary products, and White Label partner brands assembled slide by slide. Recreated for portfolio — representative structure, not live data.

Plan mode first. Then four hours to a full system.

I started in Cursor Plan mode with the problem as the Customer Experience team described it: two weeks of manual synthesis, unsustainable at ~30,000 records, Copilot chunking that left gaps in interpretation. The plan had three deliverables: a data synthesis pipeline, a live dashboard, and a presentation template wired to the same structured output.

01

Data synthesis pipeline

Ingest raw complaint and NPS files. Output structured JSON and markdown tagged by product, theme, subtheme, and sentiment.

02

Live dashboard

Product switcher across proprietary and White Label brands. Theme breakdown, MoM and YoY charts, combined NPS and complaints view, verbatims browse, insights and actions.

03

Executive report template

Same synthesised data, internal design-system monthly presentation generated by command, not assembled by hand.

4 hrs
From plan to working system: live dashboard plus generated executive report, using pre-written Cursor commands and workflow.
0
Developers on the build. Plain-English prompts, agentic Cursor, human review before publish.
100%
Of the dataset processed in one pass. No 1,000-record chunking ceiling.
Portfolio mockup of Voice of Customer dashboard with KPI cards, trend chart, and top themes

Live dashboard mockup — illustrative data, no bank branding.

Portfolio mockup of generated Voice of Customer monthly report cover

Generated exec report mockup — same data, one command.

Executive summary: insights the business can act on

The report is not a dump of charts. Synthesis surfaces ranked themes, quarter trends, and explicit recommendations product owners can run with. A generated summary page might flag a fastest-growing fee theme, NPS at a quarterly low, and a partner brand following a migration pattern the team has seen before, with a recommendation to intervene earlier than last time.

Portfolio mockup of a generated Voice of Customer executive summary with fictional metrics and generic partner labels

Generated executive summary mockup · illustrative partner portfolio · synthesised from complaints and NPS verbatims, reviewed before publish.

Designed for reuse. Next month: same five steps, same commands.

The product is not the first month's output. It is the repeatable workflow the team owns after handover. Two plain-English Cursor commands do the heavy lifting. A staging step keeps humans in control before anything goes live.

/voc/
synthesise

Read everything, tag themes, build JSON

Cursor reads the full verbatim set in one pass, applies the team's taxonomy, learns from previous syntheses, and outputs structured data. No manual categorisation row by row.

/voc/
present

Generate dashboard update and presentation

From the same synthesised files: refresh the live dashboard views and produce the monthly exec report from template.

/voc/
golive

Promote approved data to production

Staging first. The team reviews themes, insights, and verbatims before approved data moves to the live site.

Monthly workflow (five steps, one day)

01

Prepare data

Export complaints and NPS verbatims. Remove PII.

02

Run /voc/synthesise

Cursor reads everything and outputs structured data to staging.

03

Review in staging

Team validates themes, insights, and verbatims before publish.

04

Publish to live

Run /voc/golive to promote approved data.

05

Run /voc/present

Presentation generated from live data. Share and done.

Value: two weeks to one day per month · full dataset synthesis · consistent design-system output · no developer dependency.
Gotchas we designed for: AI output is a strong first draft, not gospel. Prompts need context. Staging review is mandatory. Cursor is agentic: humans stay in control.

More time fixing problems, less time analysing them.

2 wks → 1 day
Monthly reporting cycle for the Customer Experience team.
~30,000
Verbatims synthesised in one pass, with ranked themes and MoM trends across nine brands.
41 → 1
From manually rebuilt slide deck to generated report from the same live data source.

"Cursor reduces customer feedback analysis from two weeks to under a day, delivering more accurate theming at scale and a reusable, AI-powered dashboard, providing faster insights and more time spent fixing problems instead of analysing them."

— Customer Experience Lead · Partner portfolio · Personal Banking

What changed

Before After
Two weeks of manual synthesis every month One-day repeatable workflow the team runs themselves
Copilot limited to ~1,000 records per pass Full ~30,000-record dataset processed in one synthesis run
41-slide PowerPoint rebuilt from scratch Live dashboard plus generated exec report from shared data
Static monthly snapshot, hard to compare trends MoM complaint trends, theme rankings, brand switcher, verbatims browse
Analysis work owned by one person, not scalable Documented commands, staging review, and handover to the owning team

This sits alongside ADG as a Generation-phase proof on the Context Lifecycle: governed AI that turns fragmented organisational data into something teams can act on, with mandatory human review before anything ships.

The demo was the product strategy.

This build started as a live Cursor demo for Personal Banking leadership: solve a real problem in the room, hand the system to the team that owns it, show what agentic AI looks like when it respects enterprise guardrails. That framing kept the scope honest. We were not pitching a concept. We were replacing a two-week manual process with something the Customer Experience team could run next month without me in the loop.

What made it work was treating synthesis as a pipeline, not a one-off prompt. Themes learned over time. Staging existed because AI theming at scale is a strong first draft, not a final answer. The commands (/voc/synthesise, /voc/present, /voc/golive) are the product: the dashboard and the deck are outputs.

What I would do differently: invest in classification coverage tooling earlier. The dashboard surfaced a review queue for unclassified verbatims; making that visible from day one would have shortened the trust-building phase with stakeholders who were used to manually checking every row.

Four hours to build. Two weeks to one day per month. Handed to the team that runs it.

← Previous
Agentic Document Generator
Next →
Financial Wellbeing
Documentation in progress