LunaPromptsThe campus campaign is ready. The first-round calendar is not. Recruiters are trying to find interviewer hours while candidates wait for a chance to explain the projects behind their resumes.
An AI-led conversation can help collect early evidence at that stage. The quality of the handoff depends on what the round asks, how the answers are reviewed, and what the next interviewer receives.
LunaPrompts AI interviews let hiring teams conduct structured candidate conversations using AI agents. They are designed for early interview rounds, including campus recruitment and high-volume campaigns where arranging a human conversation with every applicant is difficult.
Design a useful graduate screening round
Campus recruiting leadIllustrative scenario01 / 03Choose three areas to explore
Project ownership, a debugging example, and one technical decision.
For a graduate engineering campaign, define an early-round objective: understand what the candidate personally contributed to a project and whether they can explain a technical choice. Those are narrower and more reviewable aims than “assess overall potential.”
Use a common framework with room for relevant follow-ups. Start with the project’s purpose, ask about one piece the candidate owned, and explore a failure or difficult decision. Review answers against the same role-related criteria, while allowing the examples to differ.
Tell candidates that the conversation is AI-led, what it covers, and how to reach the recruiting team if the session fails or they need an alternative arrangement. Include this information in the invitation rather than making it a surprise inside the interview.
Pilot the workflow before a large campaign. Check whether the questions are understandable, whether the output preserves useful evidence, and whether reviewers can distinguish a demonstrated skill from an unanswered question. Reserve human review capacity for the results. The next interviewer should receive a concise handoff with evidence and a proposed topic, not only a generic recommendation.
Give the first round a clear job
An early interview should help answer a defined question: does this candidate show enough relevant understanding to move to a deeper evaluation?
The answer depends on the role. For a graduate engineer, the conversation might explore a project and basic problem-solving. For an AI engineer, it might examine a workflow the candidate built, a failure they encountered, and how they evaluated the result.
Decide that purpose before choosing the interview topics. A focused first round is easier for candidates to understand and easier for reviewers to use.
Build a consistent interview framework
Start with the role's requirements and define the areas each candidate should have a chance to demonstrate. Establish what counts as supporting evidence and what requires follow-up.
Consistency does not require every conversation to be identical. Follow-up questions can clarify an answer while staying within the same skill framework. The review should still use the same role-related standards.
Keep the candidate informed that they are speaking with an AI agent, how the round fits the process, and how their responses will be reviewed. Candidates should have a clear way to raise a technical or access problem through your hiring process.
Fit AI interviews into the wider evaluation
Different companies use round names differently. In this content, an L0 round means initial screening and an L1 round means the first substantive interview. LunaPrompts AI interviews can support the early stage your team selects; define that stage clearly for candidates.
Pair the conversation with practical work when the role requires it. A candidate's description of debugging experience is useful, and seeing them diagnose a problem adds a different kind of evidence.
Human reviewers should examine the interview evidence, resolve ambiguities, and decide who moves forward. For later rounds, the existing conversation can help the interviewer avoid unnecessary repetition.
A review framework your team can use
The following is an editorial checklist for this workflow. Adapt it to the role, the candidate journey, and your configured environment.
| Review area | What to establish |
|---|---|
| Purpose | The question this round must answer |
| Framework | Common topics and relevant follow-ups |
| Candidate experience | AI disclosure, instructions, and help route |
| Handoff | Evidence, uncertainty, and human review owner |
Interview volume is not a quality measure by itself. Review whether the conversation supplies useful evidence and whether candidates can complete it as intended.
Put the guide to work
Write the first-round objective in one sentence. Remove any interview topic that does not help answer it.
Download the editable worksheet to record the decisions and open questions with your team. The examples in this guide are illustrative, not customer results or validated selection rules. Product availability and setup depend on the workflow agreed for your account.
A focused checklist, a worked scenario, and questions to resolve together.
Frequently asked questions
Are AI interviews only for campus hiring?
No. Campus hiring is a strong use case because of its volume. The same approach can support other campaigns that need structured early-stage conversations.
Does the AI interview replace all human interviews?
No. Its role is to collect useful evidence at the selected stage. Human interviews remain valuable for deeper technical discussion, collaboration, and the candidate's own questions about the team.
How are AI interviews different from calling agents?
AI interviews are substantive evaluation conversations. Calling agents can handle shorter operational tasks such as collecting information or coordinating an interview slot, and can also support a defined phone-screening workflow.
Keep building your hiring workflow
- Recruiting copilots: Give the agent a task. Give the exception a person.
- Unlimited tests: Your shortlist grew. Your test bill should not follow.
- Interview copilot: They already took the test. Make the interview add something.
Explore ai interviews with LunaPrompts or browse all 19 hiring field guides.
