← Back to the live demo Scroll, or press to step slides · ⌘P exports to PDF

KiwiSaver Copilot

An AI that explains your KiwiSaver in plain English at the exact moment you panic — and hands you to a human at the exact moment the law requires one.

Innovate AI Hackathon 2026 · BNZ × AWS × University of Auckland
Challenge 1 — AI-First Customer Experience

1 / 10

The problem

When markets fall, members burn real money panicking

A KiwiSaver balance drops, the app shows a red number with no explanation, and members make the one move that reliably hurts them: switching to cash at the bottom. The FMA measured it during COVID-19:

normal switching rate at the March 2020 low (FMA)

$1.2b

moved into lower-risk funds — locking in losses just before the recovery

$121m

is all that ever moved back

~31%

of lower-risk switches were made by members aged 26–35 — the ones with the longest horizons

April 2025 replayed the pattern: tariff announcements knocked ~10% off global shares in a week, then markets rebounded within days of the pause. Everyone who switched at the low missed the bounce.

2 / 10

The insight

The moment of panic is a service gap, not an advice gap

Members don't need someone to pick their fund at 11pm on a Tuesday. They need someone to tell them what just happened, whether it's normal, and what it means for their goal — before they act on fear. Today, at exactly that moment, the bank says nothing.

“Why is my KiwiSaver down $1,700?” is the single most answerable question in banking — every dollar of it is explainable from data BNZ already holds. It just never gets answered in time.

Regulation shapes the answer: recommending a fund is regulated financial advice under the FMC Act. Explaining a balance isn't. The product lives precisely on that line — and treats it as a feature.

3 / 10

The solution

A copilot that explains — and never advises

Embedded in the BNZ app, the copilot speaks first when something worth explaining happens, and answers the questions members actually ask:

1Proactive interceptBalance falls past a threshold → the copilot explains why before the member finds the red number alone.
2Exact decomposition“You +$166, employer +$87, fees −$14, tax −$9, markets −$829.” Accounting first; AI narrates only the market slice.
3Scenario planner“What if I contribute 8%?” “First home in 3 years?” Deterministic projections, computed live, explained in plain English.
4Human handoff“Should I switch funds?” → education plus a warm handoff to a BNZ adviser, with conversation context attached.

The live prototype next to this deck implements all four — try it.

4 / 10

AI approach

The AI narrates facts it is handed — it never invents them

Deterministic coreBalance decomposition and projections come from a calculation engine — same inputs, same answer, every time. The LLM never does arithmetic and never sees a number it could get wrong.

Grounded narrationAmazon Bedrock (Claude) receives the computed facts plus retrieved context — the fund's asset allocation, indexed market moves, curated market news — and writes the explanation. RAG, not recall.

Guardrails as complianceBedrock Guardrails encode the FMC Act advice boundary as policy: fund recommendations are structurally blocked and rerouted to adviser handoff. Compliance is architecture, not a system prompt asking nicely.

Auditable by designEvery response logs its grounding facts, retrievals and guardrail decisions — reviewable against CoFI fair-conduct obligations.

5 / 10

Technical architecture

Serverless on AWS, Bedrock at the core

ExperienceBNZ app / web
chat + charts
EdgeAPI Gateway
auth, throttling
OrchestrationCopilot service
AWS Lambda
DeterministicCalc engine
decomposition & projections
ReasoningAmazon Bedrock (Claude)
+ Guardrails: advice boundary
GroundingKnowledge Bases RAG
allocation, index moves, curated news

EventBridge watches unit prices and triggers the proactive intercept; DynamoDB holds member context; every layer is serverless, so cost scales with conversations, not headcount.

Full diagram: architecture.html (linked from the demo). The prototype mirrors this shape — static app + serverless LLM proxy — swapping Bedrock for a hosted model only because the hackathon sandbox has no AWS account.

6 / 10

Compliance

Compliance-aware by design

FMC Act — the advice line“Should I switch funds?” is regulated financial advice. The copilot educates on the trade-offs, then hands to a licensed adviser — it is structurally incapable of recommending.

CoFI — fair conductLetting members panic-switch unaided is a conduct risk. Proactively explaining losses, in plain English, is fair treatment made tangible — and logged.

No hallucinated numbersEvery figure on screen comes from the deterministic engine. The LLM's output is narration over verified facts, so a wrong number can't be generated — only a wrong sentence, which guardrails and evals police.

Human in the loopThe adviser handoff isn't a failure mode, it's the product working: the copilot warms up the conversation and attaches context, so advisers start where the member actually is.

7 / 10

Feasibility

Everything it needs, BNZ already has

The data exists todayUnit prices, transactions, contributions, fund allocations — the decomposition is a query, not a data project. No new data capture required.

Serverless economicsBedrock + Lambda means cost per conversation measured in cents, no idle infrastructure, and BNZ's existing AWS relationship.

Phased rolloutPhase 1: explain-only copilot in the app (lowest risk, immediate value). Phase 2: proactive intercepts on market events. Phase 3: scenario planning and adviser handoff integration.

Proven in miniatureThis working prototype — deterministic engine, guardrailed LLM, advice-boundary handoff — was built by students in days. The hard part isn't the technology; it's the design discipline, and that's what we're showing.

8 / 10

Impact

Fewer panicked switches, more trusted relationships

$1000s

preserved per intercepted panic switch — compounding for decades in members' balances

26–35

the age group most likely to panic-switch becomes the age group most reachable by an in-app copilot

↑ NPS

the bank that explained the crash beats the bank that sent a red number

Warm leads

every advice-boundary handoff is a qualified adviser conversation with context attached

Measurable from day one: switching rate during drawdowns vs control, copilot engagement after intercepts, adviser conversion, complaint rates. The COVID baseline means the counterfactual is already quantified.

9 / 10

Explains — never advises.

The next market shock is a certainty. Whether BNZ members meet it with an explanation or a red number is a choice.

→ Try the live prototype

KiwiSaver Copilot · Innovate AI Hackathon 2026 · Challenge 1
Simulated member data · real market events · FMA COVID-19 switching research

10 / 10