> 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/hiring-automation.md). # Hiring Automation The Hiring Automation Agent connects all your other agents, AI Matching (Resume Matching), AI Prescreening, and AI Interview, and automates how candidates move between them. Instead of manually reviewing each evaluation and deciding what to do next, you define rules once and the system handles the rest. ### What this agent does * Activates once your hiring workflow is live * Monitors evaluation signals from Resume Matching, Prescreening, and Interviews * Automatically moves candidates between stages based on rules you define * Reduces manual work and keeps your pipeline moving consistently ### 1. Rules overview and suggestions When you configure a workflow, SIA will suggest a set of automation rules based on your job role and the agents you've enabled. These suggestions give you a ready-made starting point for how candidates should flow through your pipeline.

SIA suggested automation rules

**a. Single-condition rule examples** (one signal triggers an action): * When AI Matching grade ≥ A → move to Shortlist * When AI Matching score ≥ 70 → trigger AI Prescreening * When AI Matching grade ≤ D → move to Disqualified **b. Multi-condition rule examples** (two signals must both be met): * When AI Matching grade ≥ B AND Prescreening grade ≥ B → trigger AI Interview * When AI Matching score ≥ 80 AND Interview grade ≥ B → move to Shortlist * When Prescreening grade = F AND AI Matching grade ≤ C → move to Disqualified You can accept SIA's suggestions as-is, modify them, or build your own rules from scratch. ### 2. How automation rules are structured Every automation rule follows the same structure. Think of it as "if this happens and this is true, do this."

Automation rule structure

Each rule has four parts: * **Trigger** — the event that kicks off the rule (e.g. Resume Matching is completed) * **Condition** — the grade or score that must be met (e.g. Matching grade ≥ B) * **Action type** — what kind of action to take (e.g. trigger an agent or move stage) * **Action value** — the specific outcome to apply (e.g. trigger AI Prescreening) So in plain terms: when something happens, check if the candidate meets a condition, and if they do, take an action automatically. ### 3. Managing your automation rules

Manage Automation Rules

You can manage existing rules directly from the workflow without having to rebuild anything. Supported actions: * **Edit** — update the trigger, conditions, or actions on an existing rule * **Enable / disable** — temporarily turn a rule on or off without deleting it (useful when testing or adjusting your pipeline) * **Delete** — remove a rule from the workflow entirely ### 4. How the full workflow fits together When all agents are connected through automation, here's what an end-to-end hiring pipeline looks like:
**Step 1 — AI Matching (initial filter)** Every candidate who enters the pipeline is evaluated immediately. * Grade A or B → trigger AI Prescreening * Grade C, D, or E → stay back in AI Matching stage **Step 2 — AI Prescreening (qualification layer)** Candidates invited to prescreening are evaluated once they complete the chat. * Grade A or B → trigger AI Interview **Step 3 — AI Interview (final evaluation)** Candidates receive an interview invite and are graded after completing it. * Grade A or B → move to Shortlisted Each stage acts as a filter. Only the strongest candidates make it through to the final shortlist — and it all happens automatically, without your team having to step in at every handoff. --- # 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/hiring-automation.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.