Mortgage AI performance metrics to track.
Quick answer: Track mortgage AI by verified outcomes, not messages generated. A useful scorecard counts replies, confirmed appointments and attended consultations over one period. It also shows skipped records, failed handoffs and missing data instead of hiding them in one success number. This guide includes a small fictional example.
A useful scorecard connects conversation activity to verified next steps. It also makes skipped records, failed handoffs and incomplete evidence visible instead of burying them in one success number.
Define the denominator before the result
Specify the account, date range, lead sources and eligible conversation set. Paused officers, excluded stages, stop requests and records already handled by a person should not automatically be counted as unanswered assistant failures.
Keep distinct outcomes distinct: generated reply, accepted send, delivered message, borrower response, recorded appointment, attended consultation, application and funded loan. One event does not prove the next. If delivery or attendance evidence is missing, label it unknown rather than silently treating it as success.
Build a small evidence-led scorecard
| Measure | Evidence | Caution |
|---|---|---|
| Coverage | Eligible inquiries and unresolved cases | Separate exclusions and incomplete history |
| Response speed | Inquiry time to a defined relevant response event | Show slow cases as well as an average |
| Conversation quality | Context use, relevance and human overlap | Review a consistent sample, including failures |
| Appointments | Verified bookings and separately verified attendance | Do not count a link or suggested time as booked |
| Economics | Complete costs for the same period and scope | Disclose bundled charges and omitted labor |
A worked example with fictional numbers
Imagine one seven-day cohort of 40 eligible inquiries. Count each person at most once at each stage; repeated texts do not add new people. In this fictional example, 30 people have an accepted send, 24 have confirmed delivery, eight of those 24 reply, and six of those eight have a recorded appointment.
Of the six appointments, three are confirmed attended, two have unknown attendance and one is cancelled. The same period has $180 of fully included platform, CRM, messaging and allocated review-labor costs. These are teaching numbers, not LoanWick customer results, benchmarks or a forecast.
| Question | Calculation | What the result means |
|---|---|---|
| Did accepted sends reach people? | 24 confirmed deliveries / 30 accepted sends | Six accepted sends lack delivery evidence. Keep them unknown rather than labeling them delivered or failed. |
| Who replied after confirmed delivery? | 8 people / 24 people = 33.3% | The denominator is people with delivery evidence, not generated messages or all CRM records. |
| Who booked from the eligible cohort? | 6 people / 40 eligible inquiries = 15% | Use recorded appointments, not sent booking links. This percentage is only for the fictional cohort. |
| Who attended? | 3 confirmed attended / 6 recorded appointments | Show two unknown and one cancelled separately. Unknown attendance is not a no-show. |
| What did each recorded booking cost? | $180 / 6 appointments = $30 | Includes the stated expenses for this period. It does not establish funded-loan revenue or profit. |
| What did each confirmed attendance cost? | $180 / 3 attended consultations = $60 | This result can change if the two unknown outcomes are later verified. |
Use these definitions to review your own evidence. LoanWick is not claiming that every underlying delivery, attendance or expense record is automatically collected.
Avoid unfair before-and-after claims
A new campaign, different lead source or expanded team can change outcomes independently of the assistant. Compare equivalent scopes and disclose remaining differences. A few promising conversations can guide a pilot but do not establish a conversion-rate improvement for every officer.
Read the exceptions: a repeated question can harm quality even when a text was delivered. A lower subscription bill can still be expensive if the officer must repair every handoff. Check outcomes alongside contact boundaries, opt-outs and the time required for human review.
Keep a review record people can reproduce
Document the period
Use one date range for expenses, eligible inquiries and outcomes.
Retain outcome evidence
Keep the relevant send, appointment and attendance records within approved systems.
Record uncertainty
Show missing delivery or attendance evidence instead of filling gaps with estimates.
Review changes
Compare the same definitions after configuration or workload changes.