> 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-matching-agent.md). # AI Matching Agent The AI Matching (Resume Matching) Agent is the first thing that runs when a candidate enters your hiring pipeline. It reads their resume, scores it against your job requirements, and helps you quickly figure out who's worth moving forward — without you having to read every application manually. #### What this agent does * Activates automatically once your hiring workflow is live * Runs as the first step in the pipeline, before prescreening or interviews * Scores each resume against your job description * Does not contact candidates — it's purely an evaluation tool ### 1. How AI Matching works When you set up the AI Matching (Resume Matching) step in your workflow, SIA automatically generates a default matching strategy based on your job description. You don't need to define criteria from scratch — the system reads the role and builds a scoring framework for it.

Each strategy is presented as a table with these columns:

Column	What it means
Criteria	What's being evaluated (e.g., skills match, experience relevance)
Measurement	How that criteria is pulled from the resume
Score	The weight given to this criteria in the overall score
Scoring logic	The detailed rules used to calculate the score (expandable)

By default, you'll see Criteria, Measurement, and Score at a glance. Click on the icon on the right side of matching strategy to view the full scoring logic behind any criteria

### 2. Editing your strategy with AI You can refine your resume matching strategy through a simple chat interface - no complex configuration needed.

Through the chat, you can: * Add new evaluation criteria * Adjust the score weighting for any criteria * Emphasise specific skills or experience * Tune the strategy for nuances specific to your role **First-time guidance from SIA**\ \ When you're setting up for the first time, Senseloaf's AI assistant, SIA may surface a few suggestions tailored to your specific role. These are derived from your job description and are meant to show you how the strategy can be refined.

Examples of what SIA might suggest:\ \ *- Increase weight for CRM proficiency*\ *- Add customer success metrics experience*\ *- Specify required customer success certification* **Adding extra context** Need the strategy to account for something specific to your company or team? You can upload supporting documents to give the AI more context when building or refining the strategy.

Accepted documents include: * Job briefs * Role requirement documents * Internal hiring notes Supported formats: PDF, DOC, DOCX, TXT · Max file size: 10 MB per file ### 3. Strategy versioning Every time you update the resume matching strategy, a new version is saved automatically.

Here's how versioning works: * Each update creates a new version * The most recent version is always selected by default * Previous versions are kept for reference — you can look back at any time This means you can iterate freely without worrying about losing your previous setup. {% hint style="warning" %} You can create as many versions as you like, but only the most recently generated version can be **"Approved"** {% 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-agents/ai-matching-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.