> For the complete documentation index, see [llms.txt](https://docs.senseloaf.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.senseloaf.ai/hiring-agents/ai-interview-agent.md). # AI Interview Agent The AI Interview Agent conducts structured interviews with candidates who've cleared prescreening. It uses your job context to ask the right questions, evaluates responses consistently, and frees up your team from first-round interview scheduling. ### What this agent does * Activates automatically once your hiring workflow is live * Runs after AI Prescreening in the pipeline * Sends interview invitations to qualifying candidates * Conducts interviews based on your predefined questions and settings * Evaluates candidate responses and grades them ### 1. Setting up interviews When you reach the AI Interview step in your workflow, you'll see a simple setup prompt asking what you'd like to do:

* **Continue** — proceed with the auto-generated interview setup for this role. The system already has your job context and will prepare a default interview structure. This moves you into the editing and configuration stages. * **Skip** — skip interview setup for now. You can always come back and configure it from the workflow review screen before going live. At this stage, SIA has already read your job description and will suggest a default interview structure tailored to the role — so you're not starting from zero. ### 2. Interview configuration These settings control how the interview is delivered, governed, and completed once the workflow is active. **Top-level settings**

* **Number of attempts** — how many times a candidate can attempt the interview (1, 2, or 3 attempts) * **Completion window** — how long candidates have to complete the interview after receiving their invite (3 days or 7 days or 14 days) **Advanced settings**

Click the advanced configuration action to access three sections: **1. Conversation setup** Set the messages that frame the interview experience for candidates: * **Greeting message** — shown at the start of the interview * **Ending message** — shown after the last question **2. AI governance** AI governance settings define the guardrails and proctoring rules applied during the interview. * Guardrails that control how the AI interviewer behaves * Proctoring and integrity-related checks (as configured for the organisation)

**3. Delivery setup** Control how interview invitations and reminders are sent: * Customise the invitation email content * Enable reminder messages * Set how many reminders go out (1, 2, or 3)

### 3. Managing interview questions The interview structure is a set of questions that defines what the AI interviewer asks and in what order. You can review, refine, and update this at any time. **a. Reordering and deleting questions**

For each question, you can: * **Reorder** — drag questions to set the flow you want * **Delete** — remove questions that aren't relevant for this role **b. Refining questions with AI** You can rewrite or improve individual questions using a natural language prompt. This is useful when you want to tune questions for seniority level, role specifics, or depth of evaluation.

Things you can do through the prompt: * Rephrase a question for a junior, mid-level, or senior candidate * Adjust difficulty based on role expectations * Add scenario-based or situational questions * Align questions more closely with real job responsibilities Example prompt: *"Rework this question to assess senior-level decision-making for a B2B SaaS role. Add a follow-up that probes how they collaborate with cross-functional teams."* **SIA suggestions:**

While you're editing, SIA may surface contextual suggestions to help improve question quality — especially during your first few setups. These are tailored to the job role you're hiring for, optional, and designed to show what can be refined or expanded. Examples of what SIA might suggest: * *"Generate behavioural interview questions"* * *"Create situational interview scenarios"* * *"List technical skills assessment questions"* --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.senseloaf.ai/hiring-agents/ai-interview-agent.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.