Lorikeet x PEXA

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

Incorrect password. Please try again.
2-week POC

One sprint to a decision

Offline. Two weeks. Two iteration cycles. A small set of PEXA testers reviewing ~20 calls. By the end you have enough evidence to commit or walk away.

The bar

What success looks like

Three measurable outcomes. We baseline against your current state in week 1 and report against these at the exit review.

Quality bar

≥ 90%

Of reviewed conversations rated PASS against PEXA's existing QA rubric. No regression vs a senior support agent on the same scenarios.

Containment

≥ 35%

Of in-scope conversations resolved end-to-end without human handoff in the test set. Anchored to the two POC workflows.

Compliance posture

0 breaches

Zero PII echoes, zero legal/duty advice incidents, zero unredacted artifacts. Guardrail tests run on every workflow change.

The scope

POC scope — three workstreams, one sprint

Not phased — concurrent. All three run in parallel inside the same 2-week window.

1

Two workflows, built & live

Workspace errors & lodgement, plus settlement & workspace status — the two highest-volume scenarios. Both stood up with mock tool wiring against the public PEXA playbook. KB seeded.

2

Voice + chat on the same agent

Same workflows on a Lorikeet AU voice number and the chat widget. Voice-specific tuning (chunked numerics, no URLs read aloud, settlement-day urgency) applied.

3

Coach grades the test set

Coach scores every test conversation against PEXA's QA rubric. The grade plus the theme detection feed straight into the cycle 1 review.

Timeline: 2 weeks end-to-end. Offline only — no production traffic. Day 0–2: PEXA shares SOPs & QA rubric. Lorikeet builds. Day 3–6: Cycle 1 — share, test, feedback, iterate. Day 7–10: Cycle 2 — same shape. Day 11–14: Exit review and commercial decision.

The cycle

Review & iteration

Two cycles, four steps each. Same shape we ran with Airwallex's ATO pilot. Total: ~20 conversations for PEXA to review across both cycles.

Step 01

Share & simulate

Lorikeet ships the workflows to your sandbox and runs the full simulation suite. Pass rate + transcripts shared with PEXA.

Step 02

PEXA tests

Your testers run their own calls and chats against the sandbox — same surface members would see. No setup work on your side.

Step 03

PEXA feedback

Structured feedback against the agreed rubric. Ten conversations per cycle, reviewed and scored. One short working session to walk through the failures.

Step 04

We iterate

Lorikeet incorporates the feedback overnight. Workflow + guardrail changes ship behind the simulation gate. Next cycle starts.

Total cycles
2
Conversations to review per cycle
~10
PEXA time per cycle
~3 hours per tester
Lorikeet turnaround on feedback
Overnight
The split

Responsibilities

Three buckets. No granular per-line ownership. The point is fast and simple.

PEXA provides

The inputs we need

  • SOPs and procedural docs for the two workflows
  • Help centre access (or content) for the KB
  • Your QA rubric & what "pass" means to you
  • 2–3 named testers and their availability for ~3 hours per cycle
  • One named POC lead — single point of contact
Lorikeet does

The build & run

  • Build the two workflows, KB ingest, guardrails, mock tools
  • Voice channel + chat widget on a Lorikeet sandbox
  • Simulation suite against the agreed scenarios
  • Coach grading + theme detection on the test set
  • Workflow + guardrail iteration overnight on PEXA feedback
  • Exit readout: scores, themes, decisions needed
PEXA signs off on

The gates

  • Quality bar achieved on the reviewed conversations
  • Containment hitting the agreed threshold
  • Zero compliance breaches
  • Decision to convert to a paid production deployment