# Overview

The Agent configuration is split between two files.

1. lenses-agent.conf
2. provisioning.yaml

**lenses-agent.conf** holds all the database connections and low-level options for the agent.

In [**provisioning.yaml**](https://docs.lenses.io/latest/deployment/configuration/agent/automation) you define how to connect to your Kafka cluster, Schema Registries, Kafka Connect clusters, and HQ. See [Provisioning](https://docs.lenses.io/latest/deployment/configuration/agent/automation) for more information.

{% hint style="success" %}
The **provisioning.yaml** is watched by the Agent, so any changes made, if valid, are applied.
{% endhint %}

## JSON Schema Support

To help with creating a **provisioning.yaml** from your IDE you can use the provided JSON schema support. They are available in the following repo.

<a href="https://github.com/lensesio/json-schemas" class="button primary">View JSON Schemas</a>

Add the following to the top of your YAML file

```yaml
# yaml-language-server: $schema=https://raw.githubusercontent.com/lensesio/json-schemas/refs/heads/main/agent/provisioning.schema-6.1.json
```

You will then get auto completion and validation, for example, at the start of a line type **kafka** at the start of the line to trigger the default snippets (templates) for Kafka.

For Schema registry, type Schema, Connect type Connect, Alerting type altering, etc.

{% hint style="success" %}
You require at minimum a lenses-hq connection and a kafka connection for the schema to be valid.
{% endhint %}

You do not need to use the default snippets, you can also use the auto completion for each connection type.

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJpmk4J5g3Kj2RRRpYUrl%2Fuploads%2FsjETzwctKKGxGYcYgJQn%2Fjson-schema-provisioning.mp4?alt=media&token=a2f85c93-a252-46d5-b58a-f92cc9a8b6c8>" %}


---

# Agent Instructions: 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:

```
GET https://docs.lenses.io/latest/deployment/configuration/agent/overview.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.