# Overview

## **Agentic Engineering for data streaming**

Lenses is the developer experience and governance layer for engineers and AI agents.

## How Lenses Works

<div data-full-width="false"><figure><img src="https://3629020462-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FoxgTiTb4MZT9IGHAYUTn%2Fuploads%2FLXu2NKBSpaca5O16gIHJ%2Farchitecture-6.2.png?alt=media&#x26;token=e771f63e-cb1b-4e44-9e48-e359a9d2580e" alt=""><figcaption><p>Lenses Architecture</p></figcaption></figure></div>

Lenses has two components:

{% stepper %}
{% step %}
**HQ**

HQ is the control plane / central portal where end users interact with different environments (Kafka clusters). It provides a central place to explore data across many environments.

HQ is a single binary, installed on premise or in your cloud. From HQ you create environments which represent individual Kafka clusters and their supporting services. For each environment, you deploy an agent which connects to Kafka and back to HQ.

**Environments**

Lenses defines each Kafka Cluster and supporting services, such as Schema Registries and Kafka Connect Clusters, as an environment.

{% hint style="info" %}
You can have many environments, on premise, in the cloud, provided HQ has network access to the agent and the agent can connect to your Kafka cluster or any Kafka API compatible service.
{% endhint %}

Each environment has an agent. Environments can also be assigned extra metadata such as tiers, domains and descriptions.
{% endstep %}

{% step %}
**Agents**

{% hint style="info" %}
There's a 1 to 1 relationship between environments, agents and Kafka clusters.
{% endhint %}

To explore and operate in an environment you need an agent. Agents are headless applications, deployed with connectivity to your Kafka cluster and its supporting services.

Agents only ever communicate with HQ, using an Agent key over a secure channel. You can not, as a user, interact directly with them. End users are unaware of agents, only environments.

Agents require:

1. Agent Key to establish a communication channel to HQ
2. Connectivity to a Kafka cluster and credentials to do so.

The agents acts as a proxy to read, or write to your Kafka cluster, execute queries, monitor for alerts and manage SQL Processors and Kafka Connectors.
{% endstep %}
{% endstepper %}


---

# 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/readme.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.