FeaturesBias mirror
Learn and govern

The AI points the lens at the criteria of the person deciding, too.

It compares what you prioritize with what EVO prioritizes, returns the gap in plain text, and sets each of your patterns against the real outcome of the hires.

The problem

Why this exists

How it works today

Everyone has implicit criteria, and nobody can see their own. The tools on the market sell diversity filters for the recruiter to apply to candidates; none of them returns a portrait of how the recruiter decides.

How it works with EVO

You see, side by side, which dimension you approve on more and which dimension EVO would approve on. And then you see which of the two was right, from what happened to the people who were hired.

How it works

Bias mirror from the inside

1The portrait

You prioritize trajectory three times more than evidence.

The divergence appears in paired bars, dimension by dimension, with how much each side weighs. Where you agree, it shows as aligned.

The text alongside is deliberately free of judgment: it may be a conscious strategy of yours, hunting for talent on a fast climb is a legitimate thesis, or a pattern worth watching.

It is a reading, not a call to action. There is no "fix your bias" button: the decision about your own criteria is yours.
How you compare with EVO

"You shortlist on trajectory about 3× more than on evidence: EVO tends to balance those two axes. It may be strategy (hunting for talent on a fast climb) or a pattern worth watching."

YouEVO
Trajectory
Evidence
2.8×
Hard skills
aligned
Seniority

ⓘ A reading, with nothing to click. EVO carries this context into calibrating the next assessment, and sets each of your patterns against the real outcome of the hires.

2The answer

And the real outcome says who was right.

If 71% of your trajectory-based shortlists became hires that lasted past 90 days, the pattern that looked like bias was delivering. If the evidence-based ones converted less, that shows up too.

It is what separates a mirror from a judgment: it shows the pattern and then shows the result, without deciding for you which one is right.

How EVO learned from you
Aggregate base: 247 screening decisions + 38 flags in the last 90 days.
Top rejection reasons
evidence-weak34%
seniority-below22%
skills-mismatch18%
salary-likely-above13%
Top shortlist reasons
trajectory-strong28%
evidence-strong19%
skills-strong17%
culture-fit-strong12%
Real outcome × your decisions

"Of your shortlists based on trajectory, 71% became hires that lasted past 90 days: the pattern that looked like bias is delivering. Shortlists based on evidence converted at only 45%."

Base: 17 closed processes with a recorded outcome · N is still small, read it as a trend.
Under the hood

The number is calculated; the model only narrates

In a feature about bias, the worst outcome would be the feature itself making things up. That is why the division of labor is rigid.

SQLThe divergence between you and EVO is calculated by a database query, not estimated by a model
toneThe text passes through a tone gate, with a deterministic fallback if the narration fails
NBelow the minimum sample, the card does not appear, rather than appearing with a caveat in fine print
cacheThe narration is generated once an hour, not on every opening of the screen
What comes next

How it fits into the rest of the journey

Bring a role that is hard to fill

It takes a real role to see EVO work, not a canned example.

Start using it