> For the complete documentation index, see [llms.txt](https://docs.qolaba.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.qolaba.ai/chatbot/agents/creating-an-agent.md).

# Creating an Agent

Custom agents let you define exactly how the AI behaves — its role, expertise, tone, and the knowledge it draws from. Once created, an agent is available across all your chats and can be shared within your workspace.

***

#### Step 1 — Open the Agent Creation Panel

1. Go to the **chat input area**
2. Click **Create Agent**

This opens the agent creation panel.

***

#### Step 2 — Select a Base Model

Choose the AI model your agent will run on. Consider:

* **Reasoning capability** — for analytical or research-heavy agents
* **Creativity** — for content or creative roles
* **Context length** — for agents handling long documents
* **Credit consumption** — for cost efficiency at scale

> **Important:** If you plan to attach files or knowledge bases to your agent, select a **tool-calling enabled model**. Resource attachment requires tool support.

***

#### Step 3 — Name Your Agent

Give your agent a clear, descriptive name that reflects its role.

**Examples:**

* `SaaS Marketing Strategist`
* `Retail Analytics Advisor`
* `Legal Compliance Reviewer`

Optionally, add a **tagline** — a one-line description of what the agent does. Example: *"Expert advisor for B2B SaaS growth and customer acquisition strategy."*

***

#### Step 4 — Add Resources (Optional)

Resources give your agent persistent access to structured knowledge — files and documents it references automatically in every chat.

**To enable:** Turn on the **Add Resources** switch.

You can attach resources in two ways:

**From existing Knowledge Bases** — Select any Knowledge Base you have already created and attach it to the agent. See Knowledge Bases → for how to create and manage them.

**Upload new files** — Upload documents directly to the agent.

Supported formats: PDF, CSV, DOC, DOCX, Excel, TXT

| File Type | Size Limit                  |
| --------- | --------------------------- |
| Images    | Max 20 MB                   |
| Documents | Up to 1,000 pages or 200 MB |

***

#### Step 5 — Write Agent Instructions

This is the most important step. Instructions define your agent's identity, role, expertise, and behavior — they become the system prompt the model follows in every response.

Structure your instructions across four areas:

1. **Background** — Define the professional identity.

```
You are a senior marketing strategist with 10+ years of
experience in SaaS and consumer tech.
```

2. **Role** — Specify what the agent should do.

```
Provide structured insights, campaign strategy,
and performance analysis.
```

3. **Expertise** — Define domain specialization.

```
Expert in digital acquisition, customer psychology,
and data-driven growth.
```

4. **Behavioral Instructions** — Define tone and output style.

```
Be concise and structured.
Provide step-by-step explanations.
Include actionable recommendations.
Avoid unnecessary filler.
```

{% hint style="info" %}
The more specific your instructions, the more consistent and useful your agent's outputs will be. Vague instructions produce generic behavior — treat this like writing a detailed job description.
{% endhint %}

***

#### Step 6 — Create the Agent

Once you have completed all steps, click **Create Agent**. Your agent is now available in the Agent Selector and ready to use in any chat.