Product strategy · Business analysis · AI workflow design
Rumi
A human-supervised decision system that turns structured rental enquiries into room recommendations for Leasing review.
Role
Product & BA / Delivery lead
Team
Nicole + 1 developer
Status
Shipped · 2026
Timeline
3 weeks to build
I led the Leasing discovery, designed the decision logic and human hand-off, and worked with one developer to ship the workflow.
From better enquiries to faster decisions
A new website enquiry workflow captured prospect requirements and preferences in a more structured format. But Leasing still spent 5–7 minutes checking available rooms and preparing a recommendation for each enquiry.
Rumi was built to reduce that manual work:
Apply eligibility rules to remove rooms that do not meet clear requirements.
Compare suitable rooms across factors such as location, price and room fit.
Flag anything that still needs checking for Leasing to verify.
Prepare a recommendation and draft response for Leasing to review.
See the decision logic in action
A simplified recreation of how Rumi filters available rooms, compares viable options and prepares a recommendation for Leasing review.
RK
RoomingKos
Rumi for Sales
TodayEnquiriesPropertiesAdmin
Recreated demo · not live
1
Enquiry
Applicant
Student
Budget
$350–450 / wk
Preferred area
Monash Clayton
Move-in
10 Feb
Room type
Single, solo
Mandatory
Female-only
2
Matches
FEASIBILITY CHECKS — Lease · Category · Occupancy · Move-in window · Location eligibility. REQUIREMENT CHECKS — must-have requirements are enforced where the data allows, or surfaced for human verification where it doesn’t.
3
Reply
SEND AS
FORMAT
NOTES
Built from a template I wrote — Rumi fills in the room facts and adapts tone or emphasis to Leasing instructions.
How I designed the decision system
The design decisions behind the workflow.
01Use rules for clear decisions
Availability, move-in timing and room eligibility are checked first, before any room is considered further.
AI compares the rooms that pass the rules across factors such as location, price and room fit, then explains the strongest options for Leasing to review.
AI is used after the rule-based checks, not instead of them.
03Flag what cannot be confirmed
If the available data cannot verify a requirement, Rumi flags it for Leasing. If the model fails, the workflow falls back or hands the enquiry over instead of guessing.
04Keep the final decision with Leasing
Leasing can review why each room was recommended, change the shortlist and edit the customer response before sending.
Verify · Include / Exclude · Adjust recommendation
↓
Rumi drafts response
Email / WhatsApp · Standard / Concise / Bullets
↓
Leasing customises
Edit directly · Add instructions · Regenerate
↓
Final customer response
Reduce manual work without removing Leasing's control of the recommendation or customer response.
The system doesn’t have to know everything. It should be clear about what it can decide, what it should surface, and when human judgement should take over.
DECIDE → SURFACE → HAND OVER
Outcome
Room matching & response preparation
Rumi cut room-matching and response preparation from 5–7 minutes to under one minute, giving Leasing a recommended shortlist and draft response ready to review.
5–7 min
<1 min
manual analysis → review-ready output
01
Repeatable decision flow
Room matching became more consistent, with rules, trade-offs and unconfirmed requirements shown clearly for review.
02
Faster follow-up
Leasing receives both a recommended shortlist and a draft response, reducing the work between enquiry and customer follow-up.
03
Designed to extend
The same enquiry and decision structure can later connect to CRM and operational workflows.
AI workflowDecision rulesHuman-in-the-loopFailure design