> 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/create-matching-strategy.md).
# Create Matching Strategy
Think of the matching strategy as Senseloaf's evaluation rubric for a role. It's built automatically from your job configuration, using the job title, required skills, experience range, and responsibilities, etc., so you don't have to set it up from scratch.
Once it's generated, you can review it, fine-tune the criteria, adjust scoring weights, and approve it. After approval, Senseloaf uses this strategy to rank every candidate who applies.
#### 1. Find your matching strategy
After approving a job, Senseloaf immediately generates a matching strategy for it. You don't need to trigger this manually — it happens in the background as soon as the job configuration is complete.
Matching Strategy
{% hint style="info" %}
The strategy is generated from your job configuration, so the criteria and scores you see will be specific to the role you created. A software engineering role will look very different from a sales role.
{% endhint %}
#### 2. Edit the strategy using the chatbox
On the left side of the Matching Strategy screen, you'll find a chatbox. This is how you make changes to the strategy. Instead of clicking through settings, you simply describe what you want in plain language and the system updates the criteria instantly.
Edit Strategy
Here are some examples of instructions you can type into the chatbox:
* "Increase weight for skills relevancy"
* "Add a criterion for enterprise client handling"
* "Remove the SaaS company experience criterion"
* "Set experience relevancy score to 20"
{% hint style="info" icon="pen-nib" %}
Keep your instructions short and specific. The more clearly you describe what you want, the more accurately the system will update the strategy.
{% endhint %}
#### 3. Understand how scores work
Each criterion has a score attached to it. The score represents how much weight that criterion carries in the overall candidate evaluation — higher scores mean that criterion has more influence on the final ranking.
To see exactly how a score is calculated, click the brackets icon on the right side of Matching Strategy. This expands a breakdown view showing the scoring logic behind that criterion.
Scoring Logic
The breakdown tells you which signals Senseloaf looks for in a candidate's profile, and how much each contributes to the score. This is especially useful if you want to verify the strategy is evaluating candidates the way you intend.
#### 4. Review and approve the strategy
When the criteria and scores look right, it's time to approve the strategy. Take a final pass through the list and make sure it reflects what actually matters for this role. Once approved, Senseloaf will use this strategy to evaluate and rank every candidate.
Every change you make in the matching strategy will create a new version. You can review all the versions from the drop down next to Resume Matching.
Strategy Version
{% hint style="warning" %}
You can only approve the most recent version
{% endhint %}
* Check that all criteria are relevant to the role
* Make sure score weights reflect your actual hiring priorities
* Click "Approve" when everything looks good
---
# 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/create-matching-strategy.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.