> 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/getting-started/key-concepts.md).
# Key Concepts
To get the most out of Senseloaf, it helps to understand a few core concepts. These are the fundamental building blocks used when setting up a job and running hiring workflows — once you understand how they fit together, everything else on the platform will make a lot more sense.
### 1. Job Configuration
A Job Configuration is the final, structured version of your job. Think of it as your **single source of truth** — once created, all hiring automation runs based on this.
It includes all the important details needed to run hiring workflows:
* Job title
* Location
* Experience requirements
* Employment type
* Role description
* Required skills
* Preferred skills
* Number of open positions
* Compensation range *(optional)*
### 2. Job Input
A Job Input is where your job setup begins. Before anything is processed or structured, Senseloaf needs raw information about the role, and that input can come from a number of different sources:
* Typing a job description manually
* Importing data from your Applicant Tracking System (ATS)
* Uploading documents (PDF, DOC, and other formats)
The system combines everything into one clean input before processing. This ensures nothing important is missed and avoids inconsistencies across sources.
### 3. Job Architect
The Job Architect is what converts your raw Job Input into a structured Job Configuration.
Rather than generating free-form text, it fully rebuilds the job in a well-defined structure by extracting:
* Required skills
* Preferred (nice-to-have) skills
* Implied requirements
* Experience range
* Responsibilities
* Job metadata
The goal is to produce a precise, structured output, not just a summary of what was provided.
### 4. Workflow Thread
Every job setup runs inside a **Workflow Thread**. This thread acts as the memory of the entire process — keeping track of everything from start to finish, including:
* Input data
* Intermediate versions of the job
* Feedback and changes made along the way
* Approval status
* Routing decisions
This is what makes it possible to:
* Resume a workflow if it's interrupted
* Incorporate human feedback at any stage
* Checkpoint the state of a configuration
* Debug configuration paths if something doesn't look right
### 5. Agent
Every job is linked to an **Agent** (i.e Resume Matching Agent, and AI Prescreening Agent and/or AI Interview Agent). The Agent acts as the owner of the job and manages its entire lifecycle — from initial setup through to active hiring.
During setup, the Agent helps organise and manage the job configuration. Once the workflow is live, it powers all the automation that follows, including:
* Candidate sourcing
* Screening pipelines
* Hiring workflow execution
Consider the Agent as the engine that drives your hiring workflows from the moment a job is created.
### How it all fits together
These five concepts work as a chain. A **Job Input** is processed by the **Job Architect** to produce a **Job Configuration**. The entire setup runs inside a **Workflow Thread** that tracks every change and decision. And an **Agent** is linked to the job to own and execute everything that happens next.
Once you have these five concepts in mind, you'll have a clear picture of how the system works end-to-end.
How it all fits together
---
# 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/getting-started/key-concepts.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.