A resume screen should answer one question: does this person's experience match what the role actually needs? Traditional ATS keyword filters don't answer that — they check whether specific words appear on the page. JD-aligned, seniority-weighted AI screening does answer it, and it shows its work. Here's how it works and why it changes the quality of everyone who reaches your recruiters.
Why keyword filtering fails
The classic ATS filter is a string match. You tell it "must have Kubernetes," and it rejects every resume without the literal word — including the engineer who wrote "container orchestration at scale on GKE." It also passes the resume that listed "Kubernetes" once in a skills soup with no supporting experience.
That's two failures at once: false negatives (capable people filtered out) and false positives (keyword-matchers passed through). The filter runs before any human looks, so nobody ever learns what was lost.
What JD-aligned screening does instead
JD-aligned screening starts from the actual job description, not a keyword list. It reads each requirement, then reads the resume for evidence that the requirement is met — understanding meaning, not matching strings.
- The role needs "scalability experience." The resume says "rebuilt the ingestion pipeline to handle 4M events/min." The AI recognizes that as strong evidence, even though the word "scalability" never appears.
- The role needs "team leadership." The resume says "mentored three engineers and owned the on-call rotation." Evidence found.
The output isn't a yes/no gate. It's a structured score with the evidence attached — which requirements are strongly met, which are thin, and where the gaps are.
Why seniority weighting matters
The same resume should not get the same score for every role. A candidate with two years of experience and real depth is a strong junior and a weak staff engineer — simultaneously true.
Seniority weighting adjusts how much each signal counts:
- For a senior role, scope, architectural ownership, and leadership evidence weigh heavily.
- For a junior role, trajectory and fundamentals matter more, and the absence of leadership isn't a penalty.
So the score is calibrated to the role you're actually hiring for, not a generic "good resume" score. This is the difference between screening and skimming — see the broader argument in skills-based hiring vs. resume screening.
Keyword filter vs. JD-aligned AI screening
| Keyword ATS filter | JD-aligned AI screening | |
|---|---|---|
| What it checks | Do exact terms appear? | Does real experience meet each requirement? |
| Handles synonyms/paraphrase | No | Yes |
| Calibrated to seniority | No | Yes |
| Output | Pass / reject | Score + evidence per requirement |
| False negatives | High | Low |
| Auditable | Not really | Yes — you see why |
The score is a starting point, not a verdict
The most important design choice: the AI scores, a human decides. The screen surfaces a ranked, evidence-backed shortlist to your recruiter — it doesn't silently auto-reject anyone. A person reviews the evidence and makes the call, and the strongest candidates flow straight into the next step: a live AI interview or a rubric-graded take-home.
This is the same principle that runs through Pilot: AI does the time-consuming reading and scoring; the human keeps the judgment. And when you need to search inbound and existing candidates by capability rather than keywords, the same understanding powers semantic candidate search.
The bottom line
Keyword filters optimize for how a resume is written. JD-aligned, seniority-weighted screening optimizes for whether the person can do the role — and hands your recruiters a shortlist they can trust, with the evidence to back every score. That's a screen worth running before you spend a single hour of human time. See how it fits the whole flow in the product overview.