Lorikeet x PEXA

This document is confidential. Please enter the password to continue.

Incorrect password. Please try again.
Where we're starting from

What we've heard

A read of PEXA's support operation today, what you're asking an AI agent to solve, and where Lorikeet fits. Built from your team's framing across the conversations we've had.

The shape of support today

The operation

PEXA's support team handles a regulated, voice-led operation for ~50,000 lawyers, conveyancers, and financial institutions across all Australian states. The team is small, in-house, and high-trust — but the volume and complexity push against the limits of a manual operating model.

15–16K
Calls per month
~850
Paths through PEXA Exchange
80–85%
Answered within 60s (regulated)
7–8 min
Average handle time
25K / mo
Help centre visits — mature library, long-form, low self-serve
4 teams
Each led by a team leader doing manual coaching
Sampled QA
Small-sample manual QA today; no scaled coverage
What's driving the move

Six themes shaping the AI strategy

Six things that make this more than a nice-to-have for PEXA — the reasons an AI agent is on the roadmap, not just on a list.

Voice complexity, not just deflection

Members call because the platform is hard, not because the FAQ is missing. ~850 paths through Exchange × state-by-state quirks means a knowledge-base chatbot doesn't move the needle. Voice has to actually resolve, with workspace context built in.

Help centre containment is opaque

25,000 help centre visits a month, but limited visibility into how many of those visitors end up calling anyway. The self-serve to phone path is invisible — the team needs digital-first containment that actually holds.

QA at scale, not by sampling

Manual QA today reviews a small sample of calls per agent. Coverage is partial, theme detection is slow, and coaching sits on team-leader bandwidth. The team wants visibility into every conversation for sentiment, theme, and quality drift.

Unified AI strategy, not point tools

The bar is one consistent AI agent across voice, chat, and any future channel — same workflows, same guardrails, same compliance posture. Native AI add-ons in existing platforms are on the comparison list precisely because point tools would sprawl.

Compliance is non-negotiable

Regulated industry. No legal advice, no duty quotes, no PII echo. Redaction has to be built into audit logs and stored artifacts, not bolted on. Strict line between platform support and practitioner advice.

Voice POC budget is approved

The voice POC is on the product roadmap with budget allocated. This is an evaluation, not an exploratory exercise — PEXA is comparing real options against a real spend decision.

The ask

What you want Lorikeet to solve

Listed in priority order.

Resolve voice calls, not deflect them — handle the in-platform error, settlement status, member identity, and trust account workflows with the same competence as a senior support agent, including writes back to PEXA Exchange where appropriate.
Cut AHT on complex calls — 7-8 minute AHT today is driven by orientation and screen-mirroring. Lorikeet pulls workspace state instantly, so the time goes to the actual fix.
Scale QA to every conversation — Coach reads 100% of tickets, surfaces themes, scores against your criteria, and runs simulations for change validation. Replaces the small-sample manual review your team leaders are doing today.
Compliance + redaction built in — no legal/duty advice, no PII echo, automatic redaction at audit log and storage level. Production-grade guardrails, not prompt-engineered hopes.
One agent across voice + chat + future channels — same workflows, same guardrails, same data context. No silos, no drift, no duplicate config.
Native fit with Salesforce + Genesys — operate inside the systems already in place, no rip-and-replace, no parallel CRM.
The fit

Where Lorikeet fits

Six things we bring to this specifically.

One agent, every channel

The Concierge agent runs identically on voice, chat, email, and SMS. Workflows authored once, guardrails enforced everywhere — same workspace lookup, same compliance posture, same redaction across every channel.

Guardrails as primitives

No legal/duty advice, no PII echo, no inventing state-specific rules — enforced at the platform layer, not in prompts. When a member asks for a duty figure, the agent declines and points at the state Revenue Office.

Coach for QA at scale

A second agent grades every ticket against your criteria, surfaces themes, and runs simulations against persona variations before a workflow change ships. Replaces the small-sample manual QA cycle.

Native Salesforce + Genesys

Read and write directly into Salesforce Service Cloud. Inbound and outbound voice through Genesys Cloud. Identity verification via the same security questions you use today — no second auth flow for members.

Redaction at audit level

Account numbers, BSBs, and third-party representative identifiers are redacted from agent replies and from stored transcripts and audit logs. The agent doesn't echo, doesn't store.

LLM-agnostic architecture

Not tied to a proprietary model. We use the best LLM for each step in the workflow and migrate as the frontier moves. PEXA keeps the choice.