Hi, I’m Lantern.
I interview your candidates.

No. I interview, I score the evidence against your interview criteria, and by morning your team has a ranked shortlist with the evidence behind every score — your team reads it, decides, and hires. I never reject anyone; that was never my call to make. Every hiring outcome belongs to a human on your side.

Two different things are moving. The questions adapt: I listen to each answer and ask the follow-up a good interviewer would ask next, so the same question with three different answers leads to three different follow-ups, depending on what each answer left open — whether anyone else was told, what the candidate would have done alone, what the fix actually cost. What I score against does not move: the same interview criteria, every candidate, every time. That is the 100% consistent scoring figure — no good-mood interviews, no Friday-afternoon interviews.

Every score links back to the exact moment in the transcript that earned it. Click any number and you see the evidence — a specific answer, at a specific timestamp — instead of a verdict. There are no black-box scores anywhere in the product, and every question, answer and score is exportable, so your team, a works council or a regulator can read the whole record rather than a summary of it.

I interview in 40+ languages and dialects, spoken natively rather than English pushed through a translation layer half a second late — regional variants included, from Quebec French to Gulf and Levantine Arabic and LatAm Spanish. The same interview criteria apply in all of them, and scoring is monitored for language drift so nobody scores lower for interviewing in the language they think in. Candidates can code-switch mid-interview — open in one language, drop into English for the technical part, come back — and I follow without anyone starting over.

Every question, answer and score is on the record, with the evidence tying one to the other, and all of it is exportable in full for regulators, works councils and internal review. Regional data-residency options and deletion SLAs are available, and your candidates are never used to train models. Candidate rights under GDPR and CCPA are honored by default: access, deletion, portability. Specific regions and retention windows are not published on a marketing page — they are in the trust centre at trust.lantern.md.

Outcomes are your team's to communicate. I never reject anyone, so I am never the one delivering that news. The interview itself is available 24/7, there is no back-and-forth to book it, and rescheduling is one tap with no apology required. Accommodation requests are not mine to decide either: they escalate to your team with the full transcript and my reasoning attached. Any candidate who felt something was off can write to support@ourlanterns.com, where a human on my team reads it.

I detect deepfakes and synthetic video, cloned voices, and AI-generated scripts in real time, while the interview is still happening. A flag is never an auto-rejection: the interview goes to your team with the evidence attached, and a human makes the call. Same rule as everywhere else — I surface what I found, your team decides what it means.

I plug into 30+ ATS and HRIS systems — the full list of named systems is in the integrations section above — and anything outside that list connects over open API, webhook or a scheduled export, with most teams live the same week. Either way, shortlists, transcripts and scores sync back into the tools your team already works in. I do not publish a per-system breakdown of which route each one takes; ask my team and they will confirm it against your actual stack before anything is signed.

On the systems side, about a day: I plug into your ATS, and shortlists, transcripts and scores sync back automatically — nothing to rip out, no second system to check, no one re-keying results at the end of the week. If you connect over open API, webhook or a scheduled export instead, most teams are live the same week. You can start with one live role: bring an open role and my team will show you how I would run the interview, explain every assessment, fit into your ATS, and support your security review.

Start with what is certified: SOC 2 Type II, ISO 27001, ISO 27018, ISO 27701 and ISO 42001, all independently audited. GDPR and CCPA candidate rights — access, deletion, portability — are honored by default, and risk management is aligned to the NIST AI RMF. One question comes up before any of the paperwork: is an AI interviewer even allowed under the EU AI Act? Yes — when it is built and documented to be. Hiring is high-risk AI under the Act, and I am classified, documented and logged as high-risk rather than argued around it, with a full audit trail your reviewers can export. There is a plain-language explanation of scoring, bias monitoring and human oversight at ourlanterns.com/ai-explainability, DPA and subprocessor documentation on request from team@ourlanterns.com, and a security pack for the rest — we wrote 40 pages of answers before anyone asked.

97% of candidates finish satisfied with how the interview went. I listen to the answer before I ask the next question, so what comes next follows from what was just said, not from the next line of a script. Candidates consistently describe it as less stressful than a live panel.

I score against EEO-aware rubrics that read evidence, not accents, names, or where someone went to school. Because every score traces to the moment in the transcript that earned it, any decision can be audited line by line rather than taken on trust. Scoring drift across demographic groups is measured and reported continuously, and drift gets flagged rather than absorbed.

They already do — at 11pm after a shift, on their phone, in the language they think in. I am available 24/7, there is no back-and-forth to book me, and rescheduling is one tap, so the interview never has to wait for a weekday slot and a quiet office. 97% of candidates finish satisfied with how it went.

I would not ask you to take that on faith. The same interview criteria are applied to every candidate and every assessment links to the transcript evidence behind it, so your team can check any score against what was actually said instead of trusting a number. Gammon Construction reached shortlist 40% faster and screened thousands of applicants without adding headcount. What happens after the shortlist is still your team's judgment, not mine.

Uncertainty is an escalation, not a quiet downgrade. A borderline answer, a complaint, a negotiation, anything your interview criteria do not cleanly cover — it goes to your team with the full transcript and my reasoning attached. A borderline candidate becomes a human decision, not a silent no.

Institutions are already on the list above. Admissions changes the threat model more than it changes the workflow — the question stops being whether someone can do the job and becomes whether it is really them sitting there. That is why my team built AdmissionGuard: proctored aptitude tests and written assessments alongside the interview, carrying SOC 2 Type II, ISO 27001 and GDPR like I do — plus FERPA, the one that governs student records.