> 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-workflows/plan-ai-interview.md).

# Plan AI Interview

An AI Interview is an automated interview conducted by an AI Agent. Once set up, the agent takes over the initial interview round — asking each candidate a consistent set of questions, recording their responses, and evaluating answers based on the job configuration.

This means your team spends less time on first-round interviews and more time on candidates who have already demonstrated fit.

{% hint style="info" %}
AI Interviews are configured per job. Make sure you've already created the job and set up your matching strategy before configuring this step.
{% endhint %}

#### 1. Review the auto-generated questions

As soon as you land on the AI interview setup page, Senseloaf generates a set of interview questions using your job description as input. The questions are designed to probe role-specific skills, relevant experience, and problem-solving ability — so they should already be a good fit for the role.

Take a moment to read through each question. Consider whether it covers what you actually want to learn from a candidate in this role, and note anything you'd like to change, add, or remove.

<figure><img src="/files/2FDewdsZsyzorp7NQ0lp" alt=""><figcaption><p>Review auto-generated questions</p></figcaption></figure>

{% hint style="warning" icon="info" %}
The auto-generated questions are usually a solid starting point. Rather than rewriting everything, focus on adding role-specific questions that the system might not have inferred from the JD alone.
{% endhint %}

#### 2. Customize questions using the chatbox

The setup screen has a chatbox on the left side. This is how you refine your question set — just type an instruction and the system updates the interview instantly. You don't need to edit questions one by one.

<figure><img src="/files/PDzNRf8RWmRlg9iFov4P" alt=""><figcaption><p>Customize questions</p></figcaption></figure>

Here are some examples of instructions you can type into the chatbox:

* "Add a question on handling enterprise clients"
* "Remove basic communication questions"
* "Make the churn question more specific to SaaS"
* "Add a question about cross-functional collaboration"
* "Reorder questions to start with the most important one"

{% hint style="info" %}
Keep the total number of questions reasonable — 5 to 6 is ideal for an AI interview. Too many questions can make the experience feel lengthy for candidates and harder to evaluate meaningfully.
{% endhint %}

#### 3. Configure interview settings

Along the top of the AI interview setup screen, you'll find four settings that control how the interview is delivered to candidates. Two of these are configurable via dropdown — the other two reflect the current defaults.

<figure><img src="/files/iqLO7eCWDMFQPi2sAWZ2" alt=""><figcaption><p>Configure interview settings</p></figcaption></figure>

* **Interview format -** Currently set to Fixed Interview — the AI asks all questions in a predefined order. This is the standard format for AI interviews.
* **Attempts -** Set how many times a candidate can attempt the interview. Defaults to 3. Use the dropdown to change this.
* **Completion deadline -** Set how many days a candidate has to complete the interview after receiving their invite. Defaults to 7 days.
* **Language -** The AI interview is currently conducted in English. This is the default language for all interviews at this time.

{% hint style="warning" %}
If you're hiring for a role with a tight turnaround, consider reducing the completion deadline to 3 days. For senior or harder-to-fill roles, giving candidates 14 days gives them more flexibility to fit the interview into their schedule.
{% endhint %}

#### 4. Review guardrails and proctoring settings

On the right side of the setup screen, you'll find the guardrails and proctoring settings panel. These are built-in controls that protect the integrity of the interview — making sure candidates engage with the process genuinely and aren't trying to manipulate or bypass the AI Agent.

<figure><img src="/files/JRqxzYmhyZ4VovptvJWl" alt=""><figcaption><p>Review Guardrails and Proctoring Settings</p></figcaption></figure>

* Guardrails detect when a candidate tries to manipulate or redirect the AI Agent, and automatically bring the interview back on track
* Proctoring ensures candidates are genuinely present — camera, microphone, and screen sharing are used to monitor the session throughout

{% hint style="warning" %}
The default guardrail and proctoring settings work well for most roles. You only need to adjust them if you have specific requirements - for example, enabling dual screen for roles where candidates need to read a script.
{% endhint %}

#### 5. Review and Approve

Once you're satisfied with your questions, settings, guardrails, and proctoring configuration, click "Approve". From this point on, invited candidates will be taken through the AI Interview as part of the hiring process for this role.

{% hint style="success" icon="trophy-star" %}
Your AI Interview is live. The AI Agent will now conduct interviews with candidates automatically and evaluate their responses based on your job configuration.
{% endhint %}


---

# 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-workflows/plan-ai-interview.md?ask=<question>&goal=<endgoal>
```

`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.