> 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-prescreening-agent.md). # AI Prescreening Agent Once a candidate clears the resume matching stage, the AI Prescreening Agent steps in. It sends candidates a short, structured chat-based questionnaire to check their availability, eligibility, experience, and role fit — before anyone on your team has to spend time on a call. #### What this agent does * Activates automatically once your hiring workflow is live * Runs after AI Matching (Resume Matching) in the pipeline, if enabled * Engages candidates through a chat-based questionnaire * Scores responses and flags disqualifiers automatically * Does not require a human to run — it works on its own ### 1. Setting up prescreening There are five ways to create your prescreening question set. Since the workflow already carries your job context, you can move fast — either starting from defaults or building something custom.

**a. Quick Start using your Job Description (JD)**

The fastest option. SIA reads your job description and automatically generates a complete question set — covering experience, skills, availability, and role-specific requirements. Best when you want to get started quickly and refine later. **b. Using prebuilt templates**

For common roles, Senseloaf offers ready-made prescreening templates. Each one includes: * Curated questions for that role type * Default scoring rules * Pre-set disqualifiers Select a template and the full question set loads instantly. {% hint style="info" %} You can also save your own set of questions as a template for common roles. {% endhint %} **c. Selecting by category** You can generate questions by choosing evaluation categories. Questions are auto-generated for whichever categories you select.

Available categories include: * Eligibility * Availability * Work Experience * Technical Skills * Behaviour * Personality * Visa * Notice Period **d. Generate with AI**

Paste in a list of topics, themes, or guidance and the SIA will turn it into a structured prescreening flow, with question types, scoring, and disqualifiers already set up. For example, you might paste in: "Create questions to validate experience working with enterprise customers. Ask about CRM tooling. Evaluate how candidates drive product adoption." SIA converts this into a set of ready-to-use question widgets. **e. Upload a sheet**

Click **Download** to get the official Senseloaf question template, fill it in, and upload it back. The sheet supports: * Question text * Question type * Scoring rules * Disqualifier flags {% file src="/files/oLO7Pf3Hn3J4PBo4l32Z" %} {% hint style="danger" %} Do not edit the header fields in the template — these are fixed: question\_category, question\_text, question\_type, answer\_choices, weight, disqualifier. {% endhint %} ### 2. The chat structure Prescreening questions are arranged in the exact order candidates will experience them. This means you're designing both the evaluation and the candidate experience at the same time. The flow has three parts: 1. Greeting message — An intro message shown at the start of the chat (editable) 2. Question widgets — Your prescreening questions, shown one by one 3. Ending message — A closing message after the last question (editable)

### 3. Managing individual questions Each question appears as its own widget. Here's what you can see and configure on each one:

**What's shown on each widget:** * Question text * Answer options (where applicable) * Question type (Single choice / Multiple choice / Free text) * Category tag * Scoring indicator * Disqualifier badge (if enabled) **Settings you can configure per question:**

* **Question type** — Single choice, Multiple choice, or Free text * **Scoring** — Assign scores to individual answer options * **Disqualifier** — Flag specific answers to automatically screen out candidates who don't meet a hard requirement **Actions available on each widget:**

* Reorder questions by dragging * Edit question text, options, or settings * Delete questions that aren't relevant * Add new questions to the set ### 4. Prescreening configurations

These settings control how candidates experience the prescreening once the workflow is live. **Top level:** * **Number of attempts** — how many times a candidate can attempt the prescreening **Advanced:** * **Communication setup** — choose how candidates are notified (Email or SMS), customize the message content, and set clear expectations for what they need to do ### 5. Saving as a template

Once you've set up prescreening for a role, you can save the entire configuration as a reusable template. Templates capture: * All questions in their defined order * Question types, scoring rules, and disqualifiers * Number of attempts, languages, and communication settings **Using saved templates:** * Select them when setting up prescreening for a new workflow * Use them as a starting point and customize from there * Maintain consistency across similar roles without rebuilding from scratch --- # 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-prescreening-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.