# Jack and Jill Cut Candidate Screening Costs by 88% with Jev

> Source: <https://typesafe.ai/blog/jack-jill-jev-case-study>
> Published: 2026-11-11 06:54:50+00:00

# How Jack & Jill Cut Candidate Screening Costs By 88% With Jev

We saved ~half a million dollars last week with Jev.

And our products got much better at the same time.

Matthew Wilson, Co-founder/CEO @ Jack & Jill

### Background

Jack & Jill is a talent marketplace brokered by AI agents. Jack is a career agent for top professionals and Jill is an agent for hiring teams. When Jack and Jill agree there is a mutual match, they introduce the candidate and the company directly, skipping the application altogether. To date, they’ve worked with over 5,000 companies and more than 400,000 professionals working in startups - and raised a total of $60M in the process.

Within 10 days of their first test, Jack & Jill had fully rolled out Jev in production - replacing Gemini 3.1 Flash Lite for 100% of calls for a key stage in their candidate matching pipeline.

Compared to Gemini, Jev maintained the same level of accuracy, with 88% lower cost and roughly 50% faster task completion time.

Cost savings are projected to be $500K per year - and more importantly, new use cases have been unlocked across the product, such as showing candidates matched jobs immediately after signup.

### Impact

| Result | Details | 
|---|---|
| ↓ $500K/year | Absolute projected savings | 
| ↓ 88% cost | `BEFORE \| $0.755` with Google Gemini`AFTER  \| $0.092` with TypeSafe Jev Cost per 1,000 candidates scored | 
| 2x speed | `BEFORE \| 20.3 sec`` AFTER  \| 10.3 sec` Median time to screen each candidate  | 
| No loss in quality | `BEFORE \| 93.9%` Baseline`AFTER  \| 94.6%` Candidates requested by hiring managers | 

## The challenge: expensive to screen a large volume of candidates with Gemini

#### Before Jev

1. **Candidate pool.** Every day, 6,000 candidates**for every open role** are pulled from the database
2. **Initial scoring.** A low-cost model (Gemini 3.1 Flash Lite) scores each candidate and creates a shortlist of the top 2,000 candidates
3. **Close review.** A higher-power model assesses the top 2,000 candidates, ending with a list of a few hundred candidates for the hiring manager

Even with a “low-cost” model like Gemini Flash Lite, costs were adding up fast, due to the "Initial scoring" step that assessed 6,000 candidates for every open role.

## Results with Jev: Similar quality to Gemini at 88% lower cost

#### With Jev

Before switching, Jack & Jill tested both Gemini and Jev models on 150 live roles, and the same candidates for each role.

For each role, they included:

- every past “winner”: a candidate a hiring manager later asked to meet
- a sample of remaining candidates (weighted to accurately represent the original 6,000 candidates retrieved for each role)

The test counted how many winners each model kept on the shortlist. For example, a score of 95% means that for every 100 candidates that the hiring manager asked to be introduced to, the model correctly kept 95 of them in its shortlist.

*Ultimately, Jack & Jill found that Jev was able to maintain similar quality to Gemini, with 88% lower cost and half the median time to complete scoring.*

Overall, the team expects to save more than $500K based on projected volumes over the next 12 months.

### Quality: Slightly higher than Gemini (Recall and AUC)

Jev kept slightly more winning candidates than Gemini (+0.7 percentage points), although the difference was not statistically significant (90% confidence interval of −0.4 to +1.8)

Jev also performed slightly better on AUC, a measure of how often a model ranks a winner above a randomly chosen candidate with no recorded hiring manager selection. 1.0 is perfect and 0.5 is a coin toss. Jev’s score of 0.933 means it ranked the winner higher in approximately 93.3% of those pairings, compared with 92.4% for Gemini — aligning better with the recorded hiring manager selections.

| **Measure** | **Gemini 3.1 Flash Lite** | **Jev** | 
|---|---|---|
| % winners kept in the Initial Scoring of 2,000 candidates | 93.9% | 94.6% | 
| Ranking quality (AUC) | 0.924 | 0.933 | 

### Speed: Roughly twice as fast

Median time to screen candidates dropped by 50% with Jev compared with Gemini.

| **Measure** | **Gemini 3.1 Flash Lite** | **Jev** | 
|---|---|---|
| Median time to screen all candidates for a role | 20.3s | 10.3s | 

### Cost: 88% lower token cost, $500K in projected savings

Jev's input price is a sixth of Gemini's and its output is free. As a result, the cost per 1,000 candidates with Jev is just 9 cents - compared with 76 cents with Gemini.

Just at their current volume of roles, Jack & Jill will save $265K a year. Factoring in expected growth, the team expects to save **$500K over the next twelve months.**

| **Measure** | **Gemini 3.1 Flash Lite** | **Jev** | 
|---|---|---|
| List price per million tokens | $0.25 in, $1.50 out | $0.042 in, output free | 
| Cost per 1,000 candidates screened | $0.755 | $0.092 | 

## Improving user experience by unlocking new features

Jev’s usage has expanded across more than 15 workflows across Jack & Jill's product, ultimately powering a better product experience for users. For instance:

- **Matched roles at sign-up.** Every new candidate is checked against every suitable open role straight after onboarding, for under $0.10 per candidate.
- **A near-instant profile check.** The check candidates wait on after onboarding dropped from about 3.6 seconds on Gemini to about 0.2 seconds, with better accuracy.
- **Checks across the product,** including the CV editor, company classification and marketplace filtering.

Savings from using Jev instead of Gemini in these additional features are excluded from the projections above.

## Conclusion

Within just 10 days, Jack & Jill used Jev as a “drop-in” replacement for Gemini 3.1 Flash Lite - achieving comparable results on quality, with 88% lower cost and 50% median completion time.

In addition, adopting Jev has unlocked new use cases that will power better user experience throughout Jack & Jill’s product, resulting in faster / better job matches for both hiring managers and professionals considering their next move.

###### Methodology: Quality figures come from an offline test on live roles. The $500K figure is a projection based on expected growth in search volume (cost savings based on current volume = $265K). Gemini list prices are as published by Google at the time of measurement.

∵ ⩆

⩆ ∵